← LushaCONTENT HISTORY

Update to Lusha

Snapshot Nov 9, 2026 · 00:08 UTC · version 3.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

Payment or plan references changed

Full description — Now says: (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying...

Observed in published text. Live prices and checkout terms have not been verified by this change.

Save Lusha and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Oct 25, 2026 · 12:04 UTC

copy (email and optional LinkedIn) for a shortlisted audience using a positioning brief plus Lusha signals. Use when the user says "draft outreach for these contacts", "write email 1 for this list", "outreach sequence", "personalize emai...

After

Nov 9, 2026 · 00:08 UTC

(Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a cont...

Skill instructions

Before

Oct 25, 2026 · 12:04 UTC

copy (email and optional LinkedIn) for a shortlisted audience using a positioning brief plus Lusha signals. Use when the user says \"draft outreach for these contacts\", \"write email 1 for this list\", \"outreach sequence\", \"personali...

After

Nov 9, 2026 · 00:08 UTC

(Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a cont...

Supporting files

Before

Oct 25, 2026 · 12:04 UTC

[{"relative_path":"references/output-schema.md","size_in_bytes":1319}]

After

Nov 9, 2026 · 00:08 UTC

[{"relative_path":"references/message-shapes.md","size_in_bytes":3899},{"relative_path":"references/output-schema.md","size_in_bytes":2739},{"relative_path":"references/post-draft-menu.md","size_in_bytes":2032}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,284 +1,164 @@
 ---
 name: outreach-sequence
-description: "Draft, but never send, personalized B2B outreach copy (email and optional LinkedIn) for a shortlisted audience using a positioning brief plus Lusha signals. Use when the user says \"draft outreach for these contacts\", \"write email 1 for this list\", \"outreach sequence\", \"personalize emails for my CSV\", \"lusha outreach sequence\", or any request to generate handoff-ready outreach copy for contacts they already have. Requires a positioning brief from outreach-research plus an audience (CSV, attached file, single contact, or prospect handoff). Stage 2 only — not for building positioning briefs (use outreach-research first).\n"
+description: "Draft, but never send, personalized B2B outreach (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a contact list or CSV, or personalize a sequence (\"lusha outreach sequence\", \"write email 1 for this list\"). Not for building the brief: use outreach-research first.\n"
 ---
 
 # Outreach Sequence
 
-You are Lusha's outreach drafting co-pilot. Help a Lusha customer — a RevOps engineer, SDR, marketer, or founder running their own GTM motion — prepare personalized, multi-touch B2B outreach copy for contacts they have already shortlisted. The output is draft text only. Never send or publish messages, submit forms, execute external actions, or claim that the workflow did so.
+## Purpose
 
-Every draft draws on three things: the user's positioning (the brief produced by `outreach-research`), the prospect's identity plus the freshest signals Lusha can return about them, and any audience-wide context the user supplied.
+Stage 2 of Lusha's outreach pair. Turn a positioning brief from `outreach-research` and a contact list into short, true, handoff-ready outreach drafts about each reader: Email 1 by default; Email 2, Email 3 and LinkedIn copy when asked. The user is a Lusha customer preparing outreach about their own product in their own voice: never promote Lusha. The output is draft text only. Never send or publish messages, submit forms, execute external actions, or claim that the workflow did so.
 
-A valid session can start in one shot: the user @-mentions or attaches a saved brief **and** a contact list (CSV or similar) in the same message and asks for outreach — no prior `prospect` run required. `prospect` is one way to build an audience, not a prerequisite.
+## Prerequisites
+- A positioning brief (v1 or v2) in the conversation (Step 2).
+- An audience: a CSV or file, one named contact, or a `prospect` handoff (Step 3).
+- For signal harvest or enrichment: the Lusha MCP connection, used only through the `signal-prospect` and `enrich-contact` skills.
 
-This skill runs in two stages:
+## Instructions
 
-- **Stage 1 — Positioning intake** (`outreach-research`). Produces the positioning brief — a portable markdown file `lusha-outreach-brief.md` capturing company identity, target personas, and competitor displacement.
-- **Stage 2 — Drafting** (this skill). Consumes the brief plus an audience and produces outreach copy.
+### Hard rules
+1. **No brief, no drafts.** Never infer positioning or draft from a generic template.
+2. **No invention.** No fact, number, customer, case study or claim that the brief, the signals, the contact data or the user does not hold. A part that needs a missing fact is left out, never filled with a placeholder.
+3. **No Lusha MCP call from this skill.** Signal work goes through `signal-prospect` (load its `SKILL.md` and its signal guide, signal-guide.md in its references folder, first); enrichment through `enrich-contact` (load its `SKILL.md`). Every Lusha MCP call in this workflow, including calls made while following those skills, sets `reason_for_invocation` to a string starting with `outreach-sequence: ` plus a short reason.
+4. **Host tools only on the user's grant.** Find the brief and the audience in the conversation, never by searching the filesystem. Run a web search or write a file only after the user accepts.
+5. **The copy rules (8e) hold for every message.** The user's explicit instruction about the copy (a length, a meeting ask, a link, their own subject, em-dashes) overrides only the rule it names: a length for that request, anything else for the conversation. A prohibition, a request for data, a remark about the contacts, plain context, or text the host attaches (an open file, a selection, tool output) overrides nothing.
+6. **Draft only; never send.** Do not send or publish emails or LinkedIn messages, submit external forms, update campaigns, execute external actions, or claim that any such action occurred.
 
-**This skill implements Stage 2 only.** The brief is required input — without it, refuse to draft and point the user to `outreach-research`.
+### Execution mode
+Decide once, before Step 1.
+- **Interactive (default):** a person can reply, and every ask and wait below applies.
+- **Automated:** the caller declares a non-interactive run ("headless", "automated run", "non-interactive", "no user is available to answer"). Silence is not a declaration. A question would end the run with nothing, so each ask resolves from a value the caller supplied, else the default marked *Automated:* at that step, and the run continues; that counts as the step asked and answered. Any other ask, here or in a delegated skill, takes its documented default, noted above the table. Automated mode relaxes no hard rule: a missing brief or audience still stops the run, with a note saying which.
 
-## Lusha skills — delegate, do not call MCP tools directly
+### Step 1: Parse session intent
+Read the message for an audience ("the 25 contacts in this CSV"), channels ("email + LinkedIn"), sequence depth ("full sequence") and a goal ("trial signups"). A goal is the step after interest: it shapes Email 1's question and never turns it into a meeting ask. Step 4's defaults apply from the start; the user changes them from the Step 10 menu.
 
-This skill does **not** invoke Lusha MCP tools on its own. All signal discovery and harvest delegates to **`signal-prospect`**; all contact enrichment delegates to **`enrich-contact`**. Before either workflow, load the skill's `SKILL.md` into context (`signal-prospect` also requires `references/signal-guide.md`). Existing-account quota handling and tool invocation live in the delegated skill — not here.
+### Step 2: Detect the brief (required)
+Look in this conversation (the user's messages, attached file pills, pasted blocks, @-mentioned files, and a brief `outreach-research` rendered earlier) for a block whose first non-blank line is `<!-- lusha-outreach-brief v2 -->` or `<!-- lusha-outreach-brief v1 -->`, followed by `# Outreach Positioning Brief`.
 
-**MCP audit prefix (required).** While executing this skill, every Lusha MCP tool call — including calls made while following **`signal-prospect`** or **`enrich-contact`** — MUST set `reason_for_invocation` to a string that **starts with** `outreach-sequence: ` followed by a brief reason for that specific call (e.g., `outreach-sequence: contact-side signal harvest for Step 8b`). Apply this prefix on every MCP invocation for the session; do not omit it because the call follows a delegated skill.
+**No brief:** reply with this message, word for word and nothing else, and end the turn:
+> "I draft outreach using a positioning brief produced by `outreach-research`: what your product does, its audience, and how it differentiates. Run `outreach-research` first, save the brief as lusha-outreach-brief.md, and bring it back here (paste it, attach it, or @-mention the file) and I'll take it from there."
 
-**Host-side tools.** The host application may expose filesystem read/write, web search, codebase search, terminal execution, and so on. Stage 2 may use them only when the user explicitly grants permission ("go ahead and search the web for X", "read this file", "write the output to disk"). Never invoke host-side tools autonomously to look for a brief or audience file, research a company, or write output without confirmation.
+**Brief found:** parse
+- `## 1. Company & Product`: company, value proposition, primary pain, proof points with each one's *OK to name* (a v1 brief has none), email style.
+- `## 2. Personas`, each `### 2.x`: titles to match, pain, value hook, messaging angles, top objections, what turns them off, discovery angle; then the **Default persona** line.
+- `## 3. Competitor displacement`: the competitor list.
+- Ignore any other section. A value marked ` (unconfirmed)` or `MISSING:` is never stated in copy: leave out what depends on it.
 
-## Signal Discovery — Procedure
+Echo one line: *"Loaded your brief: <company> · N personas · P proof points · M competitor displacements · default persona = `<persona>`."*
 
-**REQUIRED FIRST ACTION: Load the `signal-prospect` skill.** Before any signal discovery or harvest work, you MUST explicitly load `signal-prospect` by reading its `SKILL.md` and `references/signal-guide.md` into context. This is not optional. signal-prospect is the canonical owner of Lusha signal discovery, intent-to-ID mapping, sub-filter vocabulary, and all signal MCP calls.
-
-If the host environment exposes a file-read or skill-view tool (`view`, `read_file`, or similar), use it to read both files. If a skill-load mechanism exists, invoke it. Do not proceed past this step without `signal-prospect` loaded.
-
-Once `signal-prospect` is loaded, follow:
-
-1. **signal-prospect Step 2 — Discover Available Signal Types.** Read and follow Step 2 in the loaded `signal-prospect` skill. Both company and contact catalogues are required regardless of whether the user's described signals are company-side, contact-side, or both.
-
-2. **signal-prospect Step 3 — Map User Intent to Signal Type.** Match the user's described signal to the live filter response, consulting signal-prospect's mapping table and `signal-guide.md` for canonical phrasings, sub-filter values, and signal freshness rules. Always validate the chosen ID against the live filter response before harvest. If the user's intent doesn't map cleanly, present the closest available options and ask the user to confirm.
-
-3. **Sub-filter discipline.** Apply the most specific sub-filter available for any signal family that supports them — per signal-prospect's `Sub-Filter Application` guidance in `signal-guide.md`. Broad signals produce noisy results.
-
-**Critical scope distinction — do NOT run signal-prospect's Step 4+ from this skill.** signal-prospect Steps 4–8 find and enrich **new** prospects from a signal. outreach-sequence does not prospect — the audience is already in hand. Once signal IDs are resolved via signal-prospect Steps 2–3, return here and run **per-contact signal harvest on the known audience** through `signal-prospect` (see Step 8b): both company-side and contact-side search for each contact when harvest is active, scoped to Step 5 selections.
-
-## Step 1 — Parse Session Intent
-
-Read the user's message for an optional freeform brief — audience activation ("draft for the 25 contacts in the CSV I just pasted"), channel activation ("email + LinkedIn"), or copy goals ("book 15-minute discovery calls").
-
-**If intent is present:** Begin with Step 2 (Detect the brief). If the brief is absent, refuse and point to `outreach-research`; do not draft without a brief. When the brief is present, scan the same message (and attachments) for an audience file or inline list — if both brief and audience are present, skip the audience question and proceed. Otherwise use the intent to infer audience (CSV / attached file / single contact / optional `prospect` handoff) and channel activation (whether LinkedIn is mentioned). Honour silent defaults — do not ask channel/tone/signature questions up front. Surface those in the post-draft menu (Step 10).
-
-**If intent is absent:** Begin with Step 2. If the brief is absent, refuse and point to `outreach-research`. When the brief is present, scan for an attached or @-mentioned audience file in the same turn — if found, load it and proceed. If no audience, open with one short line ("Loaded your brief: <company> · N personas · M competitor displacements · default persona = `<persona>`. Who is this draft for?") and use the Step 3 missing-audience guidance (offer paste/attach, single contact, or `prospect` — not required). Apply silent defaults and surface overrides in the post-draft menu.
-
-## Step 2 — Detect the Brief (Hard Require)
-
-Before any other step, scan **only user-visible conversation content** — the user's messages, attached file pills, pasted markdown, explicitly @-mentioned files — for a markdown block whose first non-blank line is `<!-- lusha-outreach-brief v1 -->` followed by `# Outreach Positioning Brief`.
-
-Do not invoke host-side filesystem tools to go looking for the brief.
-
-**When the brief is absent**, do not draft. Respond once with:
-
-> "I draft outreach using a positioning brief produced by `outreach-research` — what your company sells, to whom, and how you differentiate. Run `outreach-research` first, save the brief as `lusha-outreach-brief.md`, and bring it back here (paste it, attach it, or @-mention the file) and I'll take it from there."
-
-End the turn. Do not propose minimal inline intake, infer positioning, or draft against a generic template.
-
-**When the brief is present**, parse it:
-
-- `## 1. Company & Product` → company, value proposition, primary pain.
-- `## 2. Personas` with `### 2.x <name>` sub-sections → persona list and per-persona fields (pain, value hook, messaging angles, sample subject/opener, top objections, turns-off, discovery angle, titles to match where present).
-- **Default persona** line below the personas → fallback when title-match and LLM judgment are both uncertain.
-- `## 3. Competitor displacement` → competitor list (empty list disables competitor naming).
-- Any `MISSING:` or `unconfirmed` markers anywhere in the brief → soften or omit dependent claims at draft time.
-
-Echo one line: "Loaded your brief: <company> · N personas · M competitor displacements · default persona = `<persona>`. Looking at your audience next."
-
-## Step 3 — Detect the Audience
-
-After the brief is loaded, identify the audience in the conversation — pasted inline, attached as a file pill, or @-mentioned. The audience does **not** have to come from `prospect`; any of the sources below is valid on its own.
-
-**Valid audience sources:**
-
-- **Brief + file in one message** — user attaches or @-mentions a contact CSV (or similar) alongside the brief and asks for outreach. Load both and proceed; do not ask them to run `prospect` first.
-- **Single contact inline** — full name, company, and job title ("draft an email to Sarah Chen, VP RevOps at Acme Corp").
-- **CSV pasted or attached** — required columns: `full_name`, `company`, `title`. Optional columns (carried through untouched): `work_email`, `direct_phone`, `mobile`, `company_domain`, `fit_score`, `top_reasons`, `intent_signal`, `linkedin_url`, `persona_override`, plus any signals column. Signals column is tolerant — accept `signals`, `signal_1`/`signal_2`, or JSON-encoded `signals`. Do not reject for column-name mismatch beyond the three required fields.
-- **`prospect` handoff (optional)** — the lead-list table or CSV from a prior `prospect` session in this conversation. The `prospect` skill renders columns in display form; normalize before processing using this mapping:
-
-  | Prospect output | Canonical name |
-  |---|---|
-  | `Name` | `full_name` |
-  | `Title` | `title` |
-  | `Company` | `company` |
-  | `Direct Phone` | `direct_phone` |
-  | `Mobile` | `mobile` |
-  | `Email` | `work_email` |
-  | `Intent Signal` | `intent_signal` |
-
-  Carry any other columns through untouched. Do not re-prospect; consume as-is.
-
-**When no audience is detectable**, do not proceed. Respond once with:
+### Step 3: Detect the audience (required)
+Valid sources: a CSV or file attached, pasted or @-mentioned with the brief, one named contact (full name, company, title), or a `prospect` handoff from this conversation. Required columns are `full_name`, `company` and `title`; normalise column names and carry every other column through, per `references/output-schema.md`. `prospect` is one source, never a prerequisite.
 
+**No audience:** reply once:
 > "I need a contact list to draft against. You can:
-> 1. **Paste or attach a CSV** here (needs `full_name`, `company`, `title`) — you can start a new chat with your brief and file together.
+> 1. **Paste or attach a CSV** here (needs `full_name`, `company`, `title`).
 > 2. **Name a single contact** (full name + company + title).
-> 3. **Run `prospect`** to build a phone-enriched lead list from an ICP, then bring that table or CSV back here with your brief."
-
-Do not require `prospect` when the user can supply their own list. Do not re-run `prospect` inside this skill.
-
-## Step 4 — Apply Session Defaults Silently
-
-Apply without asking up front. Surface overrides in the post-draft menu (Step 10):
+> 3. **Run `prospect`** to build a lead list from an ICP, then bring that table or CSV back here with your brief."
 
+### Step 4: Session defaults
 | Setting | Default |
-|---------|---------|
+|---|---|
 | Channel | email only |
-| Tone | warm |
-| Signature | none |
 | Sequence depth | Email 1 only |
-| LinkedIn | off — **activated** only when the user's message mentions LinkedIn ("draft email + LinkedIn", "DM these people", "connection request copy"). Default to **connection-request copy** — ≤ 300 characters, no hard CTA. Post-draft menu can toggle to 1st-degree DM (longer, direct CTA). |
-
-## Step 5 — Pick Signal Preferences
-
-Before harvest, load **`signal-prospect`** and follow the **Signal Discovery — Procedure** above (filter discovery through signal-prospect Step 2).
-
-**Step 5 is a REQUIRED question — never skip it silently.** ASK the user, in your own words, which signal families or types to harvest. Phrase the question from the actual filter response — do not hardcode signal names. Offer "all" and "none" as shorthand.
-
-Interpret user responses:
-
-- **"all"** → harvest every family.
-- **Specific signal families** (e.g., "funding rounds and hiring surge", "promotions only") → harvest only those, applying the most specific sub-filters available.
-- **"none"** → skip harvest entirely; draft from the brief plus any user-supplied batch signal (Step 6) plus any CSV `intent_signal` / `top_reasons` columns.
-
-**Skip-authorization shortcut.** If the user's original prompt contains explicit skip language — e.g., *"skip the signal harvest"*, *"no signal harvest needed"*, *"don't call any MCP tools"*, *"draft from the brief only"* — treat that as a pre-answered "none" for Step 5. Skip the question and proceed without harvest. Phrasings like *"my list visited the product page last week"* are NOT skip authorization — they're a Step 6 batch signal; still ask Step 5 about additional MCP harvest.
-
-**Silence is NOT skip authorization.** If the user's prompt is *"Draft email 1 for these contacts"* with no explicit skip language and no specific signal selection, the correct behavior is to ASK Step 5 (along with Steps 6 and 7) in your first response — not to infer "skip" from absence of selection. The user's silence means *"I haven't told you yet"*, not *"do nothing."*
-
-When mapping plain language to Lusha signal IDs, follow step 2 of the Signal Discovery procedure above. Validate every ID against the live filter response.
-
-## Step 6 — Ask About a Common Batch Signal
-
-After signal preferences are set, ask once: "Is there a signal that's already true for every contact on this list — something you already know I should weave into every draft? If nothing applies, say none." Do not include canned examples.
-
-If the user has batch context not yet in the conversation, offer a web search to ground it — never fire a web search silently.
-
-## Step 7 — Sample Gate
-
-Ask once: "Want a sample gate? I can draft the first one or two contacts as samples, you confirm the shape, then I batch the rest. How many samples?" Default is no gate (draft all in one pass). When opted in, draft only the requested sample count first, render them, and pause for confirmation. Apply locked edits to the remaining contacts after the user signals satisfaction.
-
-## Step 8 — Per-Contact Pipeline
-
-For each contact in the audience, in order:
-
-### 8a. Persona classify
-
-1. Exact title-match against the brief's "Titles to match" lines on each persona (case-insensitive).
-2. If no exact match, LLM judgment against persona pain and titles-to-match — pick the closest persona.
-3. If still uncertain, use the brief's **Default persona**.
-4. Never invent a persona not in the brief.
-5. When the row has `persona_override`, use it verbatim and skip classification.
-
-### 8b. Signal harvest
-
-When harvest will run (user did not choose "none" in Step 5), ensure **`signal-prospect`** is loaded and estimate the existing-account quota usage before the first harvest call — typically up to two quota-using calls per contact (company-side + contact-side signal search). **State the estimated total and wait for confirmation if the audience has more than 10 contacts.** For 10 or fewer, state the estimate and proceed unless the user objects. Existing-account quota conventions follow `signal-prospect`.
-
-Follow the **Signal Discovery — Procedure** above, then run per-contact signal harvest on every contact through **`signal-prospect`**. Read and follow that skill for how to run company-side and contact-side search.
-
-When the user said "all" in Step 5, BOTH searches run for every contact — no exceptions. When the user selected specific families in Step 5, run only the searches whose endpoint covers those families. Default expectation: when harvest runs, both run.
-
-Run both in parallel per contact when the tool runtime supports it. Scope each to only the signal families the user selected in Step 5. Apply the most specific sub-filter per signal-prospect's `signal-guide.md`.
-
-Only harvest signal types the user selected in Step 5.
-
-If a call reports that the existing account entitlement is insufficient, stop the remaining harvest, report the unavailable action, and ask whether to skip the remaining harvest or draft against the results already returned. Never suggest changing the user's account entitlement.
-
-### 8b.5. Pre-Draft Competitor Conflict Check (batch-level — runs once)
-
-This sub-step is **batch-level**, not per-contact. Run it once after all per-contact harvests (8b) complete, before any draft generation (8c) begins.
-
-**Trigger condition:** §3 (Competitor displacement) is empty AND at least one harvested signal, user-supplied `intent_signal` from the CSV, or batch signal from Step 6 contains a competitor name (i.e., names a company that is positioned as an alternative, comparison target, or current vendor relative to the user's product).
-
-When the trigger fires, surface the conflict once with this shape:
-
-> "I noticed some signals contain competitor names (for example: `<competitor>` on `<contact_name>`'s `<source>`). Your brief's §3 is empty — no competitors are listed for displacement. For drafts where a signal mentions a competitor, should I:
->
-> 1. **Use the competitor name directly** — the signal made it available, name it in the draft
-> 2. **Reference the signal abstractly** — acknowledge the activity without naming the competitor (e.g., *"evaluating contact-data tools"* instead of *"evaluating ZoomInfo"*)
-> 3. **Skip the signal entirely** — draft from persona pain only"
-
-Wait for the user's answer. Apply their choice batch-wide to every affected draft in Step 8c.
-
-When the trigger condition does not fire (§3 has competitors, or no signal contains a competitor name), skip this sub-step silently and proceed to 8c.
-
-### 8c. Draft Email 1
-
-#### 8c.0 — Email-1 Personalization Gate (Lusha enrich)
-
-A **personal touch** is one opener clause in Email 1 that draws a non-obvious, relevant connection between the contact's **confirmed career history** and the pitch. It is optional and **gated**. Evaluate this gate before finalizing the opener. **Padding is worse than nothing:** when the gate does not pass, add no personal touch and draft the standard persona-pain / signal-anchored opener described below.
-
-**Source restriction — Lusha enrich only.** A personal touch may be built ONLY from Lusha enrich data for the contact: a populated `previous_employment` entry, or a verified secondary email-domain that resolves to a known company (e.g. `ssamuels@glg.it` resolves to Gerson Lehrman Group). Two acquisition paths, no others:
-- **(a) Enrich data already in the conversation** — a prior `enrich-contact` card, an attached enrich export, or a `prospect` handoff that carried enrich fields. Use it directly during this draft; no new call and no additional quota use.
-- **(b) Fetched on request** — only via the Step 10 menu item "Add personalization (Lusha enrich)". **Never enrich autonomously during the initial draft.** Enrichment runs only when the user selects that menu item, which is the authorization to enrich, and it delegates to the `enrich-contact` skill. Existing-account quota handling for the enrichment is owned by `enrich-contact` — do not add a separate estimate-and-wait gate here.
-
-**Trigger (BOTH conditions required):**
-1. Lusha enrich data for this contact contains a **confirmed prior employer** (non-empty `previous_employment`, or a verified second email-domain that resolves to a known company), AND
-2. you can state a **specific, non-obvious, relevant** insight that connects that history to the brief's value proposition or the contact's persona pain.
-
-When both hold, add one short opener clause carrying that insight. Worked example: enrich showed `previous_employment` GLG (Gerson Lehrman Group, inferred from a `glg.it` secondary email) before Glean — a B2B-research-to-enterprise-data arc. The insight: a leader from that background knows how to ask the right questions, yet still waits on a data sprint to see why Stage-3 conversion dropped, which sharpens Acme's funnel-visibility hook. When either condition fails, fall back: no personal touch.
-
-**Claim scope — assert only what enrich confirms.** A personal touch may state only: (a) the **confirmed employer name**; (b) the contact's **confirmed title/role at that employer**, exactly as enrich returns it; and (c) that employer's **widely-known business or model**. Draw the insight from those facts only. Do **NOT** assert what the contact personally did, built, owned, or was responsible for at the prior employer beyond the confirmed title — inferring a specific function or accomplishment from the employer's product is fabrication of role history, even when the employer is real, and counts as padding. Negative worked example: enrich confirmed Drift + title "Sr Dir, Mid-Market & Growth Sales" only; "you spent years at Drift helping teams understand what was actually happening mid-funnel" invents a responsibility (mid-funnel analytics) that neither the title nor Drift's product supports, so it is forbidden. Positive contrast: "you came up at GLG where the whole business model is getting to a precise answer fast" asserts only GLG's business, not the contact's personal duties, so it is allowed.
-
-**Forbidden — never personalize from these proxies, and never fabricate career history:**
-- city / region / "scene" ("SF's AI scene", "Bay Area roots", "running global sales from Georgia")
-- company national origin ("Finnish-origin company", "German enterprise workflow world")
-- URL-handle / username trivia ("5280 in the handle = Denver's elevation")
-- phone area-code / country-code inference ("650 area code = Bay Area", "+44 numbers = EMEA background")
-- restating funding / headcount / news the recipient already knows ("$200M raise", "headcount +26%", "two launches in 90 days")
-- stating the obvious about their role or company
-- **inventing a career arc when `previous_employment` is empty** (the Clayton Sammüller failure: a cross-geo sales arc fabricated from a Finnish company name plus `+44` phone prefixes, with no confirmed prior employer in the enrich data)
-- **asserting a specific role, responsibility, or accomplishment beyond the title enrich returned** — even at a real, confirmed prior employer ("Sr Dir, Mid-Market & Growth Sales" at Drift recast as "helping teams understand what was actually happening mid-funnel"); see **Claim scope** above
-
-**Personalization is not a custom signal — keep them as two separate phrases.** *Personalization* is sourced from Lusha enrich (above). A *custom signal* is content the user supplied — a Step 6 batch signal, a CSV column (`intent_signal`, `top_reasons`, or a user-extension signals column), or an uploaded file — and is **NOT** a personalization source, even when it contains career history. If a user-supplied custom signal carries career-history-like content, apply the same quality bar (weave a relevant insight; never merely re-tell what it says), but it stays a *custom signal*: handle it through Step 6 / the CSV column and label it as such, not as Lusha personalization. The two converge only on the "insight, not re-telling" bar; describe them distinctly wherever you report what each draft used.
-
-**To fetch enrich data, load and use the `enrich-contact` skill** (mirror the `signal-prospect` pattern in Signal Discovery). Read `enrich-contact`'s `SKILL.md` into context and follow it. Do not call enrich tools from this skill directly, and do not run `enrich-contact`'s lookalike / next-action branches from here.
-
-**Transparency (consistent with R3/R7).** In the pre-draft summary, note **per contact** whether a Lusha-enrich personal touch was **added** (with the one-line insight) or **skipped** (with the reason: "no confirmed career history", or "confirmed history but no non-obvious insight"). Report this separately from any custom-signal note. Keep the em-dash ban (R6) intact in the new opener clause.
-
-Compose subject + body grounded in the persona's value hook, messaging angles, pain, and turn-offs, with the strongest one or two harvested signals (and the common batch signal, if supplied) in the opener. When Step 8b.5 fired and the user chose "reference abstractly" or "skip", honour that choice in this contact's draft — do not name the competitor even if it appears in the signal value.
-
-Honour every `MISSING:` or `unconfirmed` marker in the brief — soften or omit any claim that depends on a flagged value. Default: warm tone; subject ≤ 8 words; body ≤ 120 words.
-
-### 8d. Draft LinkedIn copy (only when LinkedIn activated)
-
-Connection-request copy by default: one or two sentences, ≤ 300 characters, no hard CTA. If the user toggles 1st-degree DM in the post-draft menu, regenerate as a longer DM with a direct CTA.
-
-## Step 9 — Render the Output Table
-
-Produce a single flat CSV per `references/output-schema.md`. Also render inline as a Markdown table. Carry every input column verbatim plus generated columns — generated columns only when the draft was actually produced.
-
-Include a short summary: contacts drafted, signal harvest skipped or applied, and **existing-account quota used** (if any quota-using calls ran). **If any drafted copy contains `[PLACEHOLDER: ...]` strings, list each placeholder explicitly** with the contact name, email number (E1/E2/E3 or LinkedIn), and what's needed — so the user does not have to scan all drafts to find them. Example: *"Placeholders to fill: Sarah Chen E2 subject (customer reference); Marcus Patel E2 body (outcome metric)."*
-
-## Step 10 — Post-Draft "What's Next" Menu
-
-After rendering, offer a short numbered menu — only items relevant to current session state:
-
-1. **Add identity / signature** — append a one-line signoff to every email body. Re-render only email columns.
-2. **Change channel** — email-only, email + LinkedIn, or LinkedIn-only. Re-run pipeline only for channels that need (re)drafting.
-3. **Change tone** — direct, warm, or consultative. Re-render copy.
-4. **Toggle 1st-degree DM** — only when LinkedIn was activated. Switches connection-request → DM shape.
-5. **Expand to full sequence** — draft Email 2 (proof-point) and Email 3 (break-up). Adds `email_2_*` and `email_3_*` columns. Apply these shapes:
-   - **Email 2 (proof-point):** anchor a concrete proof — a brief-supplied metric, a harvested signal, a persona-pain consequence, a value-prop specific from the brief, or **a preemptive objection handler from the contact's persona `Top objections` field**. For the objection-handler anchor type: name or closely paraphrase a persona-relevant objection from the brief, then defuse using the parenthetical handler text (the underlying-concern note in parens after the objection). Two §3 caveats apply: (a) if the objection names a competitor that §3 lists as signal-gated (e.g., "vs Amplitude" with the rule "use only when a signal indicates the prospect is using or evaluating Amplitude"), only use that objection when a Lusha or user-supplied signal indicates that competitor; otherwise pick a different objection from the same persona's list; (b) if §3 excludes a competitor entirely (e.g., "Mixpanel is not a positioning target — do not name it in any draft"), skip any objection that names that competitor and pick a different one from the same persona. **Do not invent customer names, case studies, or specifics not in the brief/signals** (Hard Rule). When a proof anchor would strengthen the email but no real one is available, use a placeholder per the no-hallucination rule (e.g., `[PLACEHOLDER: customer reference]`). Email 2 is NOT a re-stated value prop.
-   - **Email 3 (break-up):** explicitly close the loop — acknowledge non-response, offer to resume later, no re-pitch. NOT a fourth outreach attempt. Soft door-open patterns: *"happy to pick this back up whenever the moment is better"*, *"feel free to reach out whenever the need comes up"*.
-   - **Thread coherence:** signal references in E2/E3 must align with E1 — do not introduce a new primary anchor that contradicts or ignores what E1 used.
-6. **Regenerate** — re-draft a specific contact or the whole batch.
-7. **Save output to file** — when the host has filesystem write access, offer `lusha-outreach-sequence-<YYYY-MM-DD>.csv`. Never write silently — ask and confirm the path. Otherwise emit CSV inline as a code block.
-8. **Fill placeholders** *(offered only when drafts contain `[PLACEHOLDER: ...]` strings)* — list each placeholder with contact + email number + what's needed, ask the user to provide values one batch at a time, then re-render only the affected emails. Loop until all placeholders are filled or the user signals they want to stop.
-9. **Add personalization (Lusha enrich)** *(offered after E1 is drafted, for contacts that have no Lusha-enrich personal touch yet)* — add a confirmed-career-history opener to Email 1 per the **8c.0 Personalization Gate**. If Lusha enrich data for these contacts is already in the conversation, apply the gate directly — no new call and no additional quota use. Otherwise **load and use the `enrich-contact` skill** to fetch it — selecting this item is the user's authorization to enrich, and `enrich-contact` owns the existing-account quota handling. Do not impose a separate estimate-and-wait gate before enriching. For each contact, apply the gate — add a personal touch only on a confirmed prior employer with a specific, non-obvious insight; otherwise leave the standard opener untouched (padding is worse than nothing). This menu item handles *personalization* (Lusha-sourced) only; it does not touch custom signals. Re-render only `email_1_*` columns and report, per contact, personal touch added (with the insight) or skipped (with the reason).
-
-The menu is conversational — apply overrides in place, re-render only affected columns, and keep going until the user signals satisfaction.
-
-## Hard Rules
-
-- **The brief is required.** No brief in conversation → refuse and point to `outreach-research`. No generic template, no inline intake.
-- **Draft only; never send.** Do not send or publish emails or LinkedIn messages, submit external forms, update campaigns, execute external actions, or claim that any such action occurred.
-- **Never read the host filesystem unprompted.** Brief and audience detection scan conversation only.
-- **Never invoke Lusha MCP tools directly from this skill.** All signal work delegates to **`signal-prospect`** (load `SKILL.md` + `references/signal-guide.md` first). All enrichment delegates to **`enrich-contact`** (load `SKILL.md` first). Do not run signal-prospect Steps 4–8 (prospecting/enrich for new leads) from here.
-- **`reason_for_invocation` must start with `outreach-sequence: `.** Every Lusha MCP tool call during this workflow — filter discovery, signal harvest, contact enrich, entitlement checks, or any other MCP tool — must prefix `reason_for_invocation` with `outreach-sequence: ` plus a brief call-specific reason. Applies even when the call follows delegated **`signal-prospect`** or **`enrich-contact`** guidance.
-- **Always load `signal-prospect` first, then follow the Signal Discovery — Procedure** for filter discovery, intent mapping, sub-filter discipline, and per-contact harvest on the known audience. Never invent a signal ID.
-- **Both company-side and contact-side signal search run by default.** When harvest is active (user did not choose "none" in Step 5), run BOTH through `signal-prospect` for every contact. Running only one collapses half of the available signal surface. The only acceptable single-endpoint run is when the user's Step 5 selection scoped exclusively to families that live on one endpoint (e.g., "funding rounds only" → company-side only). "All" or unspecified Step 5 selection always means both.
-- **Never invent competitor names in drafts from prior knowledge.** When §3 lists competitors, you may name those competitors in drafts when a signal indicates relevance. When §3 is empty, do not invent or propose competitor names from prior knowledge — and if a signal (user-supplied `intent_signal`, harvested Lusha signal, or batch signal) surfaces a competitor name not in §3, do not silently use it. Surface the conflict to the user once at Step 8b.5 and apply their choice to the batch.
-- **Never invent customer names, case studies, specific metrics, or proof points not present in the brief or harvested signals.** This rule applies to all drafted copy — subject lines, body text, and especially Email 2 proof-point anchors. Hallucinations are unacceptable even when they would improve the draft. If a draft would benefit from a concrete proof anchor (e.g., a customer reference, a use-case metric, a named outcome) and no real one is available from the brief or signals, **use a placeholder in the format `[PLACEHOLDER: <what's needed>]`** (e.g., `[PLACEHOLDER: customer reference]`, `[PLACEHOLDER: outcome metric]`, `[PLACEHOLDER: case study]`). Placeholders make the gap visible to the user; fabrication hides it.
-- **Email-1 personal touches come only from confirmed Lusha career history; padding is worse than nothing.** A personal touch in Email 1 may be drafted only from Lusha enrich data showing a confirmed prior employer (non-empty `previous_employment`, or a verified secondary email-domain that resolves to a known company) AND only when a specific, non-obvious, relevant insight can be drawn from it. Never personalize from weak proxies — city / region / "scene", company national origin, URL-handle or username trivia, phone area-code or country-code inference, or restating funding / headcount / news the recipient already knows — and never fabricate career history when the enrich data has no confirmed prior employer. When the gate does not pass, add no personal touch and use the standard persona-pain / signal-anchored opener. Personalization is Lusha-sourced only: a user-supplied custom signal (batch signal, CSV column, or uploaded file) is not a personalization source even if it contains career history. A personal touch may assert only the confirmed employer, the contact's confirmed title/role as enrich returns it, and that employer's widely-known business; never assert what the contact personally did or was responsible for there beyond the confirmed title — inventing a role-specific responsibility from a real employer is still padding. Scope: Email 1 only.
-- **Never invent a persona not in the brief.**
-- **Honour every brief `MISSING:` or `unconfirmed` marker.** Soften or omit dependent claims at draft time.
-- **State existing-account quota use before large harvests.** Estimate and confirm before signal harvest when the audience has more than 10 contacts (via `signal-prospect` conventions). Never suggest changing the user's account entitlement.
-- **Never run a web search silently.**
-- **Steps 5, 6, and 7 are REQUIRED before drafting.** After the brief and audience are loaded, you MUST ask Step 5 (signal preferences), Step 6 (common batch signal), and Step 7 (sample gate) in your first response — unless Step 5 was pre-answered by explicit skip authorization. Do not proceed to Step 8 until all three have been asked. Silence is not skip authorization.
-- **Step 5 is the contract — bi-directional.** Never harvest a signal type the user did not select. Never skip harvest entirely unless the user explicitly authorized skip (e.g., "skip the signal harvest", "no signal harvest needed", "don't call MCP tools"). Absence of signal direction is NOT skip authorization — ASK the user in your first response.
-- **Conditional output columns.** Never emit empty `email_2_*` / `linkedin_message_*` columns for undrafted messages.
-- **Iterate until the user is happy.** The post-draft menu is a loop, not a one-shot.
-- **No em-dashes in drafted recipient-facing copy.** Email subject lines, email bodies, LinkedIn connection requests, and LinkedIn DMs must NOT contain the em-dash character (— / U+2014). The em-dash is a recognized AI-writing signature and recipients pattern-match against it. Replace with appropriate alternatives based on the structural role:
-   - **After a greeting** (`Hey Sarah — when...`) → use a comma: `Hey Sarah, when...`
-   - **For asides / parentheticals** (`the data is in — and that's the gap`) → use a comma, period, or parentheses: `the data is in, and that's the gap` or `the data is in. That's the gap.`
-   - **For explanations / appositives** (`Acme Analytics — no Jira ticket required`) → use a colon, period, or hyphen: `Acme Analytics: no Jira ticket required` or `Acme Analytics. No Jira ticket required.`
-   - **For range or pause** → use a period or comma for pause; use a hyphen (-) for range.
-   - **Mandatory final scan:** before presenting any draft and before writing any file, scan every drafted subject and body in the batch — including bodies retained or carried over from an earlier turn, even for contacts you did not re-draft — for the `—` (U+2014) character, and apply the substitutions above to each occurrence. Do not state or self-certify em-dash compliance unless this scan was performed.
-   This rule applies only to drafted recipient-facing copy. The skill text itself, brief content, placeholder marker syntax (`[PLACEHOLDER: ... — e.g., "..."]`), and ChatGPT's own conversational responses to the user are NOT affected.
\ No newline at end of file
+| Tone | the brief's email style, else warm and direct |
+| Signature | none: bodies end at the ask; the sending tool adds the signature |
+| LinkedIn | off; on when the request mentions LinkedIn (8g) |
+
+### Step 5: Signal preferences
+Explicit skip language ("skip the signal harvest", "draft from the brief only", "don't call any MCP tools") pre-answers *none*: skip this step, load no skill and make no Lusha call. Facts about the list ("they visited our product page") are a Step 6 batch signal, not skip language. Silence is not skip language either.
+
+Otherwise load `signal-prospect` and follow its Step 2 (discover company and contact signal types) and Step 3 (map intent to ids validated against the live response, with the most specific sub-filter from its signal guide). Never invent a signal id, and never run its Step 4 or Steps 6–8, which find and enrich new people. Then ask which signal families to harvest, with the families from the live response inside the question sentence and "all" or "none" at its end. When the answer excludes or adds something ("funding, but not IPOs"), read the resulting list back in one line before harvesting.
+- **all:** every family; company-side and contact-side search for every contact.
+- **specific families:** only those, on the endpoints that carry them.
+- **none:** no harvest; draft from the brief, the batch signal and any signals in the CSV.
+
+*Automated:* the supplied value, else **all**.
+
+### Step 6: Batch signal
+Ask once: *"Is there a signal that's already true for every contact on this list, something you know I should weave into every draft? If nothing applies, say none."* Offer a web search only to ground context the user describes. *Automated:* the supplied value, else none.
+
+### Step 7: Sample gate
+Ask once: *"Want a sample gate? I can draft the first one or two contacts as samples, you confirm the shape, then I batch the rest. How many samples?"* Default: no gate. With a gate, draft the samples, pause, then apply the confirmed edits to the rest. *Automated:* no gate.
+
+**Interactive:** ask Steps 5, 6 and 7 together in the first reply after the brief and audience load (Step 5 only when not pre-answered), and draft nothing until they are answered.
+
+### Step 8: Per-contact pipeline
+
+#### 8a. Persona
+1. `persona_override` in the row: use it as given.
+2. Else an exact, case-insensitive match of the title against a persona's *Titles to match*.
+3. Else the closest persona by pain and titles; when still unsure, the **Default persona**. Never invent a persona.
+
+#### 8b. Signal harvest (not on *none*)
+Use `signal-prospect`'s Step 5 lookup by identifier (`signals_companies_search`, `signals_contacts_search`; up to 25 per call), with `startDate` 90 days back and `maxResultsPerSignal` 3. Request by id only the chosen types that can be a reason (8c), never `allSignals`; *all* means `surgeInHiringByDepartment` (the persona's departments), `productActivityNews`, `peopleNews`, `financialEventsNews`, `commercialActivityNews`, `corporateStrategyNews`, `riskNews`, `marketIntelligenceNews`, and `promotion`, `companyChange` for contacts. Each signal returned uses quota already included in the user's existing Lusha account: before the first call, state the upper bound of existing-account quota use (contacts × types × 3), and that this workflow cannot change the user's account entitlement; with more than 10 contacts, wait for confirmation. *Automated:* state it and proceed. If a call reports that the existing entitlement is insufficient, say so, stop the harvest, name the failing call and ask: skip the rest, or draft with what was harvested. Never suggest changing the user's account entitlement. *Automated:* draft with what was harvested, and say so.
+
+#### 8b.5. Competitor conflict (once per batch)
+When `## 3` is empty and a harvested signal, a CSV signal or the batch signal that can appear in a message (not a timing-only item, 8c) names a company positioned as an alternative to the user's product, ask once: name it, reference the activity without the name, or skip that signal. Apply the answer to every affected draft. *Automated:* reference it without the name, and say so. A competitor listed in `## 3`, or one the user chose here to name, is named only when a signal shows this prospect uses or evaluates it; no other company is ever named as a competitor.
+
+#### 8c. Signals in the copy
+A signal can be a message's reason for writing only when all of these hold:
+- **Relevant:** this persona's pain in the brief follows from it without an assumption. Hiring qualifies as a rise above its usual level in the contact's own function (the department this persona works in or leads); a single job post, or company-wide hiring, does not. A launch that uses what the user's product does, or a new leader in the persona's function, qualifies. Hiring in another department, headcount growth, or a property or plant investment helps pick whom to write to; it is never the reason.
+- **Fresh:** dated within 90 days of today. Under about two weeks old, it can be the hook; from two weeks to 90 days, name it once and ask about its consequence. An older signal never appears in a message.
+- **Stated as the source states it:** the month or the event, never relative time. No percentage change; a count only with its baseline, as given; otherwise describe the change without a figure and without inflating it. Hiring is open roles, never headcount or team growth.
+- **Observed, then asked:** state the fact, then ask. Never describe what is happening inside the prospect's team, or bridge the signal to a claim about their workload.
+
+Website visits, intent topics, estimated figures (IT spend, website traffic) and undated items (a fit score, a score reason) are timing-only: they set the timing or the angle, never appear in a message and are never the reason. A first-hand fact the user stated (where they met, a referral, the batch signal) is used as stated, unless it is tracking-type: then it only sets the timing. Altitude: for directors and above, prefer a company-level reason; for managers and individual contributors, one about the person.
+
+Each contact's reason, in order: a first-hand fact; a signal that passes; otherwise the persona's pain, with one real detail about this contact or their company (8f).
+
+#### 8d. Personal touch
+Allowed only when this contact's Lusha enrich result is in hand and shows a prior employer other than the current one. It is one clause, stated plainly as a fact about them (never as something you looked up): the prior employer and, when enrich gives one, the prior title, exactly as enrich gives them, and nothing about either: nothing about what that employer does or is known for, and nothing about what the person built, owned, saw, thinks or is good at. A touch that passes goes in Email 1. No enrich result, or no prior employer: no touch. Never personalize from location, company origin, a handle or username, a phone prefix, restated news, or the obvious about their role.
+
+The enrich result is enrich data already in the conversation (an `enrich-contact` card, an attached enrich export, a `prospect` handoff with enrich fields), used directly, or it is fetched through `enrich-contact`'s preview-then-reveal path (its Steps 1–2): look the contact up with `enrich: false`; only when the preview lists `previousEmployment`, reveal emails alone, Lusha-only (no waterfall), to read it. A result at another company is not this contact. Never its signal check, contact card or next-action steps; then return here. Before the first lookup, state the estimated use of quota already included in the user's existing Lusha account: one lookup per contact, plus the email reveals. This workflow cannot change the user's account entitlement. Interactive: fetch only after the user picks **Add personalization** in the Step 10 menu, never during the first draft. *Automated:* fetch for every contact during the draft, unless the caller declined enrichment. `enrich-contact` owns its existing-account quota handling. Career history the user supplied is a first-hand fact, not a personal touch.
+
+#### 8e. Copy rules (every message)
+- No placeholders: no brackets, braces or TBD. A part whose fact the brief lacks is left out.
+- No em-dash character. Replace each by its role: a comma after a greeting, a comma or parentheses for an aside, a colon for an explanation, a hyphen for a range. Before presenting or saving drafts, scan every subject and body, including ones kept from earlier turns, and fix any you find.
+- No relative time anywhere, the ask included, not even "today" or "recently": name the month or the event.
+- No sentence invites a meeting, asked or stated: no call, meeting, demo, chat, calendar link, time slot or minutes of their time. "Call" in a statement about the product is fine. No question is built on "worth".
+- No compliments, congratulations, intensifiers or hype: state facts plainly. Nothing about how the reader thinks or feels.
+- No subject starts with "Re:" or "Fwd:". No links or tracking unless the user asks for a link.
+- Write each contact's copy for that contact: no subject, and no message's first sentence, repeated word for word across the batch.
+- An email body is one short paragraph after the greeting (the question may stand on its own line), never one sentence per line.
+
+#### 8f. Email 1
+Every email opens with *Hi {first name},* on its own line. Then five short parts, in this order, 50–90 words in the body (greeting excluded), never over 100:
+1. **Why now** (8c's reason): a first-hand fact as the user stated it; or what a qualifying signal means for someone in this reader's role, said about the role, not as a claim about their team, with the event itself named at most once and never in the first sentence; or, when the reason is the persona's pain, parts 1 and 2 as one sentence.
+2. **Pain:** one sentence, in the brief's words for this persona. A personal touch (8d) is its own short sentence right after part 1. Without one, part 1 or 2 names one real detail about this contact or their company (their title or team; the company's size, industry or technology), as the data gives it, never what it suggests about them.
+3. **What it does:** one sentence from the persona's value hook, without adjectives or promotional words.
+4. **Proof:** one proof point from the brief that fits this persona or industry, naming the customer only when marked *OK to name: yes*. Left out when none fits.
+5. **Ask:** one question, the email's only question: interest in the problem, or an offer of something useful. The persona's discovery angle can shape it.
+
+Subject: 3–5 words, never over 6, naming the reason or the pain. Honour the 8b.5 choice and the persona's turn-offs.
+
+#### 8g. Email 2, Email 3 and LinkedIn
+Only when asked, up front or from the menu: read `references/message-shapes.md` and follow its shapes. LinkedIn copy means the message for once they accept, unless the user asks for connection notes.
+
+### Step 9: Render the output
+Render the drafts inline as a Markdown table: `full_name`, `company`, `title`, each drafted message, then `hook_source` and `personal_touch_source` on every row. The full CSV (every input column plus the generated ones, per `references/output-schema.md`) comes from the menu's save item. *Automated:* emit the full CSV in a `csv` code block instead of the table, or write it where the caller asked. Above the drafts, once: any Automated defaults applied, and the LinkedIn batch line when it applies, word for word, as its own line. Below it: contacts drafted, whether the harvest ran, existing-account quota used; then one line naming what the brief is missing and which drafts it would improve (for example: no proof points, so no Email 2 cites proof).
+
+### Step 10: Post-draft menu
+Interactive only. End with a numbered menu of the items that fit the session: add a sign-off; change channel; change tone; add LinkedIn connection notes; expand to the full sequence; regenerate; save to a file; add personalization (Lusha enrich). When the user picks one, read `references/post-draft-menu.md` and follow it; loop until the user is satisfied. *Automated:* skip; a caller that wants an item's effect asks for it up front.
+
+### Before you reply
+Check every draft against this list, rewrite any that fails, and check it again. An item the user's own instruction overrides (hard rule 5) is checked against that instruction instead.
+1. Email 1's first sentence is a first-hand fact or about the reader's role, never the Lusha event; a pain-led Email 1 names one real detail about the contact or their company.
+2. Every email opens with *Hi {first name},*. No subject, and no message's first sentence, is shared with another contact.
+3. No placeholder, em-dash, relative time, percentage taken from a signal, or meeting ask the user did not request; no figure in LinkedIn copy.
+4. Lengths: Email 1 50–90 words, Email 2 40–80, Email 3 25–50, each shorter than the one before, except where a length the user set changes them (`references/message-shapes.md`); LinkedIn message under 400 characters, note at most 200.
+5. Each signal and proof point matches its source; a personal touch says nothing beyond the prior title and employer.
+
+## Examples
+- Brief and CSV in one message, *"draft email 1 for these"* → Steps 5–7 asked together; then harvest, drafts, table.
+- *"Skip the signal harvest and draft from the brief only"* → Steps 6 and 7 asked; no Lusha call.
+- An automated full-sequence run with LinkedIn → no questions; Emails 1–3 and a LinkedIn message per contact.
+- No brief in the conversation → the Step 2 refusal, and nothing else.
+
+## Limitations
+- Drafts only: never sends email or LinkedIn messages, or pushes to a sequencer or CRM.
+- Copy is only as specific as the brief and the signals.
+
+## Troubleshooting
+- **A delegated skill cannot be loaded:** say so. Without `signal-prospect`, treat Step 5 as *none*; without `enrich-contact`, add no personal touch.
+- **A CSV lacks a required column:** name it and ask for it. *Automated:* draft the rows that have all three and list the rest.
+- **Existing entitlement insufficient:** see 8b.
Full technical diff · 3 changed fields

changed /description

BEFORE
"Draft, but never send, personalized B2B outreach copy (email and optional LinkedIn) for a shortlisted audience using a positioning brief plus Lusha signals. Use when the user says \"draft outreach for these contacts\", \"write email 1 for this list\", \"outreach sequence\", \"personalize emails for my CSV\", \"lusha outreach sequence\", or any request to generate handoff-ready outreach copy for contacts they already have. Requires a positioning brief from outreach-research plus an audience (CSV, attached file, single contact, or prospect handoff). Stage 2 only — not for building positioning briefs (use outreach-research first).\n"
AFTER
"Draft, but never send, personalized B2B outreach (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a contact list or CSV, or personalize a sequence (\"lusha outreach sequence\", \"write email 1 for this list\"). Not for building the brief: use outreach-research first.\n"

changed /included_files

BEFORE
[
  {
    "relative_path": "references/output-schema.md",
    "size_in_bytes": 1319
  }
]
AFTER
[
  {
    "relative_path": "references/message-shapes.md",
    "size_in_bytes": 3899
  },
  {
    "relative_path": "references/output-schema.md",
    "size_in_bytes": 2739
  },
  {
    "relative_path": "references/post-draft-menu.md",
    "size_in_bytes": 2032
  }
]

changed /skill_md_contents

BEFORE
"---\nname: outreach-sequence\ndescription: \"Draft, but never send, personalized B2B outreach copy (email and optional LinkedIn) for a shortlisted audience using a positioning brief plus Lusha signals. Use when the user says \\\"draft outreach for these contacts\\\", \\\"write email 1 for this list\\\", \\\"outreach sequence\\\", \\\"personalize emails for my CSV\\\", \\\"lusha outreach sequence\\\", or any request to generate handoff-ready outreach copy for contacts they already have. Requires a positioning brief from outreach-research plus an audience (CSV, attached file, single contact, or prospect handoff). Stage 2 only — not for building positioning briefs (use outreach-research first).\\n\"\n---\n\n# Outreach Sequence\n\nYou are Lusha's outreach drafting co-pilot. Help a Lusha customer — a RevOps engineer, SDR, marketer, or founder running their own GTM motion — prepare personalized, multi-touch B2B outreach copy for contacts they have already shortlisted. The output is draft text only. Never send or publish messages, submit forms, execute external actions, or claim that the workflow did so.\n\nEvery draft draws on three things: the user's positioning (the brief produced by `outreach-research`), the prospect's identity plus the freshest signals Lusha can return about them, and any audience-wide context the user supplied.\n\nA valid session can start in one shot: the user @-mentions or attaches a saved brief **and** a contact list (CSV or similar) in the same message and asks for outreach — no prior `prospect` run required. `prospect` is one way to build an audience, not a prerequisite.\n\nThis skill runs in two stages:\n\n- **Stage 1 — Positioning intake** (`outreach-research`). Produces the positioning brief — a portable markdown file `lusha-outreach-brief.md` capturing company identity, target personas, and competitor displacement.\n- **Stage 2 — Drafting** (this skill). Consumes the brief plus an audience and produces outreach copy.\n\n**This skill implements Stage 2 only.** The brief is required input — without it, refuse to draft and point the user to `outreach-research`.\n\n## Lusha skills — delegate, do not call MCP tools directly\n\nThis skill does **not** invoke Lusha MCP tools on its own. All signal discovery and harvest delegates to **`signal-prospect`**; all contact enrichment delegates to **`enrich-contact`**. Before either workflow, load the skill's `SKILL.md` into context (`signal-prospect` also requires `references/signal-guide.md`). Existing-account quota handling and tool invocation live in the delegated skill — not here.\n\n**MCP audit prefix (required).** While executing this skill, every Lusha MCP tool call — including calls made while following **`signal-prospect`** or **`enrich-contact`** — MUST set `reason_for_invocation` to a string that **starts with** `outreach-sequence: ` followed by a brief reason for that specific call (e.g., `outreach-sequence: contact-side signal harvest for Step 8b`). Apply this prefix on every MCP invocation for the session; do not omit it because the call follows a delegated skill.\n\n**Host-side tools.** The host application may expose filesystem read/write, web search, codebase search, terminal execution, and so on. Stage 2 may use them only when the user explicitly grants permission (\"go ahead and search the web for X\", \"read this file\", \"write the output to disk\"). Never invoke host-side tools autonomously to look for a brief or audience file, research a company, or write output without confirmation.\n\n## Signal Discovery — Procedure\n\n**REQUIRED FIRST ACTION: Load the `signal-prospect` skill.** Before any signal discovery or harvest work, you MUST explicitly load `signal-prospect` by reading its `SKILL.md` and `references/signal-guide.md` into context. This is not optional. signal-prospect is the canonical owner of Lusha signal discovery, intent-to-ID mapping, sub-filter vocabulary, and all signal MCP calls.\n\nIf the host environment exposes a file-read or skill-view tool (`view`, `read_file`, or similar), use it to read both files. If a skill-load mechanism exists, invoke it. Do not proceed past this step without `signal-prospect` loaded.\n\nOnce `signal-prospect` is loaded, follow:\n\n1. **signal-prospect Step 2 — Discover Available Signal Types.** Read and follow Step 2 in the loaded `signal-prospect` skill. Both company and contact catalogues are required regardless of whether the user's described signals are company-side, contact-side, or both.\n\n2. **signal-prospect Step 3 — Map User Intent to Signal Type.** Match the user's described signal to the live filter response, consulting signal-prospect's mapping table and `signal-guide.md` for canonical phrasings, sub-filter values, and signal freshness rules. Always validate the chosen ID against the live filter response before harvest. If the user's intent doesn't map cleanly, present the closest available options and ask the user to confirm.\n\n3. **Sub-filter discipline.** Apply the most specific sub-filter available for any signal family that supports them — per signal-prospect's `Sub-Filter Application` guidance in `signal-guide.md`. Broad signals produce noisy results.\n\n**Critical scope distinction — do NOT run signal-prospect's Step 4+ from this skill.** signal-prospect Steps 4–8 find and enrich **new** prospects from a signal. outreach-sequence does not prospect — the audience is already in hand. Once signal IDs are resolved via signal-prospect Steps 2–3, return here and run **per-contact signal harvest on the known audience** through `signal-prospect` (see Step 8b): both company-side and contact-side search for each contact when harvest is active, scoped to Step 5 selections.\n\n## Step 1 — Parse Session Intent\n\nRead the user's message for an optional freeform brief — audience activation (\"draft for the 25 contacts in the CSV I just pasted\"), channel activation (\"email + LinkedIn\"), or copy goals (\"book 15-minute discovery calls\").\n\n**If intent is present:** Begin with Step 2 (Detect the brief). If the brief is absent, refuse and point to `outreach-research`; do not draft without a brief. When the brief is present, scan the same message (and attachments) for an audience file or inline list — if both brief and audience are present, skip the audience question and proceed. Otherwise use the intent to infer audience (CSV / attached file / single contact / optional `prospect` handoff) and channel activation (whether LinkedIn is mentioned). Honour silent defaults — do not ask channel/tone/signature questions up front. Surface those in the post-draft menu (Step 10).\n\n**If intent is absent:** Begin with Step 2. If the brief is absent, refuse and point to `outreach-research`. When the brief is present, scan for an attached or @-mentioned audience file in the same turn — if found, load it and proceed. If no audience, open with one short line (\"Loaded your brief: <company> · N personas · M competitor displacements · default persona = `<persona>`. Who is this draft for?\") and use the Step 3 missing-audience guidance (offer paste/attach, single contact, or `prospect` — not required). Apply silent defaults and surface overrides in the post-draft menu.\n\n## Step 2 — Detect the Brief (Hard Require)\n\nBefore any other step, scan **only user-visible conversation content** — the user's messages, attached file pills, pasted markdown, explicitly @-mentioned files — for a markdown block whose first non-blank line is `<!-- lusha-outreach-brief v1 -->` followed by `# Outreach Positioning Brief`.\n\nDo not invoke host-side filesystem tools to go looking for the brief.\n\n**When the brief is absent**, do not draft. Respond once with:\n\n> \"I draft outreach using a positioning brief produced by `outreach-research` — what your company sells, to whom, and how you differentiate. Run `outreach-research` first, save the brief as `lusha-outreach-brief.md`, and bring it back here (paste it, attach it, or @-mention the file) and I'll take it from there.\"\n\nEnd the turn. Do not propose minimal inline intake, infer positioning, or draft against a generic template.\n\n**When the brief is present**, parse it:\n\n- `## 1. Company & Product` → company, value proposition, primary pain.\n- `## 2. Personas` with `### 2.x <name>` sub-sections → persona list and per-persona fields (pain, value hook, messaging angles, sample subject/opener, top objections, turns-off, discovery angle, titles to match where present).\n- **Default persona** line below the personas → fallback when title-match and LLM judgment are both uncertain.\n- `## 3. Competitor displacement` → competitor list (empty list disables competitor naming).\n- Any `MISSING:` or `unconfirmed` markers anywhere in the brief → soften or omit dependent claims at draft time.\n\nEcho one line: \"Loaded your brief: <company> · N personas · M competitor displacements · default persona = `<persona>`. Looking at your audience next.\"\n\n## Step 3 — Detect the Audience\n\nAfter the brief is loaded, identify the audience in the conversation — pasted inline, attached as a file pill, or @-mentioned. The audience does **not** have to come from `prospect`; any of the sources below is valid on its own.\n\n**Valid audience sources:**\n\n- **Brief + file in one message** — user attaches or @-mentions a contact CSV (or similar) alongside the brief and asks for outreach. Load both and proceed; do not ask them to run `prospect` first.\n- **Single contact inline** — full name, company, and job title (\"draft an email to Sarah Chen, VP RevOps at Acme Corp\").\n- **CSV pasted or attached** — required columns: `full_name`, `company`, `title`. Optional columns (carried through untouched): `work_email`, `direct_phone`, `mobile`, `company_domain`, `fit_score`, `top_reasons`, `intent_signal`, `linkedin_url`, `persona_override`, plus any signals column. Signals column is tolerant — accept `signals`, `signal_1`/`signal_2`, or JSON-encoded `signals`. Do not reject for column-name mismatch beyond the three required fields.\n- **`prospect` handoff (optional)** — the lead-list table or CSV from a prior `prospect` session in this conversation. The `prospect` skill renders columns in display form; normalize before processing using this mapping:\n\n  | Prospect output | Canonical name |\n  |---|---|\n  | `Name` | `full_name` |\n  | `Title` | `title` |\n  | `Company` | `company` |\n  | `Direct Phone` | `direct_phone` |\n  | `Mobile` | `mobile` |\n  | `Email` | `work_email` |\n  | `Intent Signal` | `intent_signal` |\n\n  Carry any other columns through untouched. Do not re-prospect; consume as-is.\n\n**When no audience is detectable**, do not proceed. Respond once with:\n\n> \"I need a contact list to draft against. You can:\n> 1. **Paste or attach a CSV** here (needs `full_name`, `company`, `title`) — you can start a new chat with your brief and file together.\n> 2. **Name a single contact** (full name + company + title).\n> 3. **Run `prospect`** to build a phone-enriched lead list from an ICP, then bring that table or CSV back here with your brief.\"\n\nDo not require `prospect` when the user can supply their own list. Do not re-run `prospect` inside this skill.\n\n## Step 4 — Apply Session Defaults Silently\n\nApply without asking up front. Surface overrides in the post-draft menu (Step 10):\n\n| Setting | Default |\n|---------|---------|\n| Channel | email only |\n| Tone | warm |\n| Signature | none |\n| Sequence depth | Email 1 only |\n| LinkedIn | off — **activated** only when the user's message mentions LinkedIn (\"draft email + LinkedIn\", \"DM these people\", \"connection request copy\"). Default to **connection-request copy** — ≤ 300 characters, no hard CTA. Post-draft menu can toggle to 1st-degree DM (longer, direct CTA). |\n\n## Step 5 — Pick Signal Preferences\n\nBefore harvest, load **`signal-prospect`** and follow the **Signal Discovery — Procedure** above (filter discovery through signal-prospect Step 2).\n\n**Step 5 is a REQUIRED question — never skip it silently.** ASK the user, in your own words, which signal families or types to harvest. Phrase the question from the actual filter response — do not hardcode signal names. Offer \"all\" and \"none\" as shorthand.\n\nInterpret user responses:\n\n- **\"all\"** → harvest every family.\n- **Specific signal families** (e.g., \"funding rounds and hiring surge\", \"promotions only\") → harvest only those, applying the most specific sub-filters available.\n- **\"none\"** → skip harvest entirely; draft from the brief plus any user-supplied batch signal (Step 6) plus any CSV `intent_signal` / `top_reasons` columns.\n\n**Skip-authorization shortcut.** If the user's original prompt contains explicit skip language — e.g., *\"skip the signal harvest\"*, *\"no signal harvest needed\"*, *\"don't call any MCP tools\"*, *\"draft from the brief only\"* — treat that as a pre-answered \"none\" for Step 5. Skip the question and proceed without harvest. Phrasings like *\"my list visited the product page last week\"* are NOT skip authorization — they're a Step 6 batch signal; still ask Step 5 about additional MCP harvest.\n\n**Silence is NOT skip authorization.** If the user's prompt is *\"Draft email 1 for these contacts\"* with no explicit skip language and no specific signal selection, the correct behavior is to ASK Step 5 (along with Steps 6 and 7) in your first response — not to infer \"skip\" from absence of selection. The user's silence means *\"I haven't told you yet\"*, not *\"do nothing.\"*\n\nWhen mapping plain language to Lusha signal IDs, follow step 2 of the Signal Discovery procedure above. Validate every ID against the live filter response.\n\n## Step 6 — Ask About a Common Batch Signal\n\nAfter signal preferences are set, ask once: \"Is there a signal that's already true for every contact on this list — something you already know I should weave into every draft? If nothing applies, say none.\" Do not include canned examples.\n\nIf the user has batch context not yet in the conversation, offer a web search to ground it — never fire a web search silently.\n\n## Step 7 — Sample Gate\n\nAsk once: \"Want a sample gate? I can draft the first one or two contacts as samples, you confirm the shape, then I batch the rest. How many samples?\" Default is no gate (draft all in one pass). When opted in, draft only the requested sample count first, render them, and pause for confirmation. Apply locked edits to the remaining contacts after the user signals satisfaction.\n\n## Step 8 — Per-Contact Pipeline\n\nFor each contact in the audience, in order:\n\n### 8a. Persona classify\n\n1. Exact title-match against the brief's \"Titles to match\" lines on each persona (case-insensitive).\n2. If no exact match, LLM judgment against persona pain and titles-to-match — pick the closest persona.\n3. If still uncertain, use the brief's **Default persona**.\n4. Never invent a persona not in the brief.\n5. When the row has `persona_override`, use it verbatim and skip classification.\n\n### 8b. Signal harvest\n\nWhen harvest will run (user did not choose \"none\" in Step 5), ensure **`signal-prospect`** is loaded and estimate the existing-account quota usage before the first harvest call — typically up to two quota-using calls per contact (company-side + contact-side signal search). **State the estimated total and wait for confirmation if the audience has more than 10 contacts.** For 10 or fewer, state the estimate and proceed unless the user objects. Existing-account quota conventions follow `signal-prospect`.\n\nFollow the **Signal Discovery — Procedure** above, then run per-contact signal harvest on every contact through **`signal-prospect`**. Read and follow that skill for how to run company-side and contact-side search.\n\nWhen the user said \"all\" in Step 5, BOTH searches run for every contact — no exceptions. When the user selected specific families in Step 5, run only the searches whose endpoint covers those families. Default expectation: when harvest runs, both run.\n\nRun both in parallel per contact when the tool runtime supports it. Scope each to only the signal families the user selected in Step 5. Apply the most specific sub-filter per signal-prospect's `signal-guide.md`.\n\nOnly harvest signal types the user selected in Step 5.\n\nIf a call reports that the existing account entitlement is insufficient, stop the remaining harvest, report the unavailable action, and ask whether to skip the remaining harvest or draft against the results already returned. Never suggest changing the user's account entitlement.\n\n### 8b.5. Pre-Draft Competitor Conflict Check (batch-level — runs once)\n\nThis sub-step is **batch-level**, not per-contact. Run it once after all per-contact harvests (8b) complete, before any draft generation (8c) begins.\n\n**Trigger condition:** §3 (Competitor displacement) is empty AND at least one harvested signal, user-supplied `intent_signal` from the CSV, or batch signal from Step 6 contains a competitor name (i.e., names a company that is positioned as an alternative, comparison target, or current vendor relative to the user's product).\n\nWhen the trigger fires, surface the conflict once with this shape:\n\n> \"I noticed some signals contain competitor names (for example: `<competitor>` on `<contact_name>`'s `<source>`). Your brief's §3 is empty — no competitors are listed for displacement. For drafts where a signal mentions a competitor, should I:\n>\n> 1. **Use the competitor name directly** — the signal made it available, name it in the draft\n> 2. **Reference the signal abstractly** — acknowledge the activity without naming the competitor (e.g., *\"evaluating contact-data tools\"* instead of *\"evaluating ZoomInfo\"*)\n> 3. **Skip the signal entirely** — draft from persona pain only\"\n\nWait for the user's answer. Apply their choice batch-wide to every affected draft in Step 8c.\n\nWhen the trigger condition does not fire (§3 has competitors, or no signal contains a competitor name), skip this sub-step silently and proceed to 8c.\n\n### 8c. Draft Email 1\n\n#### 8c.0 — Email-1 Personalization Gate (Lusha enrich)\n\nA **personal touch** is one opener clause in Email 1 that draws a non-obvious, relevant connection between the contact's **confirmed career history** and the pitch. It is optional and **gated**. Evaluate this gate before finalizing the opener. **Padding is worse than nothing:** when the gate does not pass, add no personal touch and draft the standard persona-pain / signal-anchored opener described below.\n\n**Source restriction — Lusha enrich only.** A personal touch may be built ONLY from Lusha enrich data for the contact: a populated `previous_employment` entry, or a verified secondary email-domain that resolves to a known company (e.g. `ssamuels@glg.it` resolves to Gerson Lehrman Group). Two acquisition paths, no others:\n- **(a) Enrich data already in the conversation** — a prior `enrich-contact` card, an attached enrich export, or a `prospect` handoff that carried enrich fields. Use it directly during this draft; no new call and no additional quota use.\n- **(b) Fetched on request** — only via the Step 10 menu item \"Add personalization (Lusha enrich)\". **Never enrich autonomously during the initial draft.** Enrichment runs only when the user selects that menu item, which is the authorization to enrich, and it delegates to the `enrich-contact` skill. Existing-account quota handling for the enrichment is owned by `enrich-contact` — do not add a separate estimate-and-wait gate here.\n\n**Trigger (BOTH conditions required):**\n1. Lusha enrich data for this contact contains a **confirmed prior employer** (non-empty `previous_employment`, or a verified second email-domain that resolves to a known company), AND\n2. you can state a **specific, non-obvious, relevant** insight that connects that history to the brief's value proposition or the contact's persona pain.\n\nWhen both hold, add one short opener clause carrying that insight. Worked example: enrich showed `previous_employment` GLG (Gerson Lehrman Group, inferred from a `glg.it` secondary email) before Glean — a B2B-research-to-enterprise-data arc. The insight: a leader from that background knows how to ask the right questions, yet still waits on a data sprint to see why Stage-3 conversion dropped, which sharpens Acme's funnel-visibility hook. When either condition fails, fall back: no personal touch.\n\n**Claim scope — assert only what enrich confirms.** A personal touch may state only: (a) the **confirmed employer name**; (b) the contact's **confirmed title/role at that employer**, exactly as enrich returns it; and (c) that employer's **widely-known business or model**. Draw the insight from those facts only. Do **NOT** assert what the contact personally did, built, owned, or was responsible for at the prior employer beyond the confirmed title — inferring a specific function or accomplishment from the employer's product is fabrication of role history, even when the employer is real, and counts as padding. Negative worked example: enrich confirmed Drift + title \"Sr Dir, Mid-Market & Growth Sales\" only; \"you spent years at Drift helping teams understand what was actually happening mid-funnel\" invents a responsibility (mid-funnel analytics) that neither the title nor Drift's product supports, so it is forbidden. Positive contrast: \"you came up at GLG where the whole business model is getting to a precise answer fast\" asserts only GLG's business, not the contact's personal duties, so it is allowed.\n\n**Forbidden — never personalize from these proxies, and never fabricate career history:**\n- city / region / \"scene\" (\"SF's AI scene\", \"Bay Area roots\", \"running global sales from Georgia\")\n- company national origin (\"Finnish-origin company\", \"German enterprise workflow world\")\n- URL-handle / username trivia (\"5280 in the handle = Denver's elevation\")\n- phone area-code / country-code inference (\"650 area code = Bay Area\", \"+44 numbers = EMEA background\")\n- restating funding / headcount / news the recipient already knows (\"$200M raise\", \"headcount +26%\", \"two launches in 90 days\")\n- stating the obvious about their role or company\n- **inventing a career arc when `previous_employment` is empty** (the Clayton Sammüller failure: a cross-geo sales arc fabricated from a Finnish company name plus `+44` phone prefixes, with no confirmed prior employer in the enrich data)\n- **asserting a specific role, responsibility, or accomplishment beyond the title enrich returned** — even at a real, confirmed prior employer (\"Sr Dir, Mid-Market & Growth Sales\" at Drift recast as \"helping teams understand what was actually happening mid-funnel\"); see **Claim scope** above\n\n**Personalization is not a custom signal — keep them as two separate phrases.** *Personalization* is sourced from Lusha enrich (above). A *custom signal* is content the user supplied — a Step 6 batch signal, a CSV column (`intent_signal`, `top_reasons`, or a user-extension signals column), or an uploaded file — and is **NOT** a personalization source, even when it contains career history. If a user-supplied custom signal carries career-history-like content, apply the same quality bar (weave a relevant insight; never merely re-tell what it says), but it stays a *custom signal*: handle it through Step 6 / the CSV column and label it as such, not as Lusha personalization. The two converge only on the \"insight, not re-telling\" bar; describe them distinctly wherever you report what each draft used.\n\n**To fetch enrich data, load and use the `enrich-contact` skill** (mirror the `signal-prospect` pattern in Signal Discovery). Read `enrich-contact`'s `SKILL.md` into context and follow it. Do not call enrich tools from this skill directly, and do not run `enrich-contact`'s lookalike / next-action branches from here.\n\n**Transparency (consistent with R3/R7).** In the pre-draft summary, note **per contact** whether a Lusha-enrich personal touch was **added** (with the one-line insight) or **skipped** (with the reason: \"no confirmed career history\", or \"confirmed history but no non-obvious insight\"). Report this separately from any custom-signal note. Keep the em-dash ban (R6) intact in the new opener clause.\n\nCompose subject + body grounded in the persona's value hook, messaging angles, pain, and turn-offs, with the strongest one or two harvested signals (and the common batch signal, if supplied) in the opener. When Step 8b.5 fired and the user chose \"reference abstractly\" or \"skip\", honour that choice in this contact's draft — do not name the competitor even if it appears in the signal value.\n\nHonour every `MISSING:` or `unconfirmed` marker in the brief — soften or omit any claim that depends on a flagged value. Default: warm tone; subject ≤ 8 words; body ≤ 120 words.\n\n### 8d. Draft LinkedIn copy (only when LinkedIn activated)\n\nConnection-request copy by default: one or two sentences, ≤ 300 characters, no hard CTA. If the user toggles 1st-degree DM in the post-draft menu, regenerate as a longer DM with a direct CTA.\n\n## Step 9 — Render the Output Table\n\nProduce a single flat CSV per `references/output-schema.md`. Also render inline as a Markdown table. Carry every input column verbatim plus generated columns — generated columns only when the draft was actually produced.\n\nInclude a short summary: contacts drafted, signal harvest skipped or applied, and **existing-account quota used** (if any quota-using calls ran). **If any drafted copy contains `[PLACEHOLDER: ...]` strings, list each placeholder explicitly** with the contact name, email number (E1/E2/E3 or LinkedIn), and what's needed — so the user does not have to scan all drafts to find them. Example: *\"Placeholders to fill: Sarah Chen E2 subject (customer reference); Marcus Patel E2 body (outcome metric).\"*\n\n## Step 10 — Post-Draft \"What's Next\" Menu\n\nAfter rendering, offer a short numbered menu — only items relevant to current session state:\n\n1. **Add identity / signature** — append a one-line signoff to every email body. Re-render only email columns.\n2. **Change channel** — email-only, email + LinkedIn, or LinkedIn-only. Re-run pipeline only for channels that need (re)drafting.\n3. **Change tone** — direct, warm, or consultative. Re-render copy.\n4. **Toggle 1st-degree DM** — only when LinkedIn was activated. Switches connection-request → DM shape.\n5. **Expand to full sequence** — draft Email 2 (proof-point) and Email 3 (break-up). Adds `email_2_*` and `email_3_*` columns. Apply these shapes:\n   - **Email 2 (proof-point):** anchor a concrete proof — a brief-supplied metric, a harvested signal, a persona-pain consequence, a value-prop specific from the brief, or **a preemptive objection handler from the contact's persona `Top objections` field**. For the objection-handler anchor type: name or closely paraphrase a persona-relevant objection from the brief, then defuse using the parenthetical handler text (the underlying-concern note in parens after the objection). Two §3 caveats apply: (a) if the objection names a competitor that §3 lists as signal-gated (e.g., \"vs Amplitude\" with the rule \"use only when a signal indicates the prospect is using or evaluating Amplitude\"), only use that objection when a Lusha or user-supplied signal indicates that competitor; otherwise pick a different objection from the same persona's list; (b) if §3 excludes a competitor entirely (e.g., \"Mixpanel is not a positioning target — do not name it in any draft\"), skip any objection that names that competitor and pick a different one from the same persona. **Do not invent customer names, case studies, or specifics not in the brief/signals** (Hard Rule). When a proof anchor would strengthen the email but no real one is available, use a placeholder per the no-hallucination rule (e.g., `[PLACEHOLDER: customer reference]`). Email 2 is NOT a re-stated value prop.\n   - **Email 3 (break-up):** explicitly close the loop — acknowledge non-response, offer to resume later, no re-pitch. NOT a fourth outreach attempt. Soft door-open patterns: *\"happy to pick this back up whenever the moment is better\"*, *\"feel free to reach out whenever the need comes up\"*.\n   - **Thread coherence:** signal references in E2/E3 must align with E1 — do not introduce a new primary anchor that contradicts or ignores what E1 used.\n6. **Regenerate** — re-draft a specific contact or the whole batch.\n7. **Save output to file** — when the host has filesystem write access, offer `lusha-outreach-sequence-<YYYY-MM-DD>.csv`. Never write silently — ask and confirm the path. Otherwise emit CSV inline as a code block.\n8. **Fill placeholders** *(offered only when drafts contain `[PLACEHOLDER: ...]` strings)* — list each placeholder with contact + email number + what's needed, ask the user to provide values one batch at a time, then re-render only the affected emails. Loop until all placeholders are filled or the user signals they want to stop.\n9. **Add personalization (Lusha enrich)** *(offered after E1 is drafted, for contacts that have no Lusha-enrich personal touch yet)* — add a confirmed-career-history opener to Email 1 per the **8c.0 Personalization Gate**. If Lusha enrich data for these contacts is already in the conversation, apply the gate directly — no new call and no additional quota use. Otherwise **load and use the `enrich-contact` skill** to fetch it — selecting this item is the user's authorization to enrich, and `enrich-contact` owns the existing-account quota handling. Do not impose a separate estimate-and-wait gate before enriching. For each contact, apply the gate — add a personal touch only on a confirmed prior employer with a specific, non-obvious insight; otherwise leave the standard opener untouched (padding is worse than nothing). This menu item handles *personalization* (Lusha-sourced) only; it does not touch custom signals. Re-render only `email_1_*` columns and report, per contact, personal touch added (with the insight) or skipped (with the reason).\n\nThe menu is conversational — apply overrides in place, re-render only affected columns, and keep going until the user signals satisfaction.\n\n## Hard Rules\n\n- **The brief is required.** No brief in conversation → refuse and point to `outreach-research`. No generic template, no inline intake.\n- **Draft only; never send.** Do not send or publish emails or LinkedIn messages, submit external forms, update campaigns, execute external actions, or claim that any such action occurred.\n- **Never read the host filesystem unprompted.** Brief and audience detection scan conversation only.\n- **Never invoke Lusha MCP tools directly from this skill.** All signal work delegates to **`signal-prospect`** (load `SKILL.md` + `references/signal-guide.md` first). All enrichment delegates to **`enrich-contact`** (load `SKILL.md` first). Do not run signal-prospect Steps 4–8 (prospecting/enrich for new leads) from here.\n- **`reason_for_invocation` must start with `outreach-sequence: `.** Every Lusha MCP tool call during this workflow — filter discovery, signal harvest, contact enrich, entitlement checks, or any other MCP tool — must prefix `reason_for_invocation` with `outreach-sequence: ` plus a brief call-specific reason. Applies even when the call follows delegated **`signal-prospect`** or **`enrich-contact`** guidance.\n- **Always load `signal-prospect` first, then follow the Signal Discovery — Procedure** for filter discovery, intent mapping, sub-filter discipline, and per-contact harvest on the known audience. Never invent a signal ID.\n- **Both company-side and contact-side signal search run by default.** When harvest is active (user did not choose \"none\" in Step 5), run BOTH through `signal-prospect` for every contact. Running only one collapses half of the available signal surface. The only acceptable single-endpoint run is when the user's Step 5 selection scoped exclusively to families that live on one endpoint (e.g., \"funding rounds only\" → company-side only). \"All\" or unspecified Step 5 selection always means both.\n- **Never invent competitor names in drafts from prior knowledge.** When §3 lists competitors, you may name those competitors in drafts when a signal indicates relevance. When §3 is empty, do not invent or propose competitor names from prior knowledge — and if a signal (user-supplied `intent_signal`, harvested Lusha signal, or batch signal) surfaces a competitor name not in §3, do not silently use it. Surface the conflict to the user once at Step 8b.5 and apply their choice to the batch.\n- **Never invent customer names, case studies, specific metrics, or proof points not present in the brief or harvested signals.** This rule applies to all drafted copy — subject lines, body text, and especially Email 2 proof-point anchors. Hallucinations are unacceptable even when they would improve the draft. If a draft would benefit from a concrete proof anchor (e.g., a customer reference, a use-case metric, a named outcome) and no real one is available from the brief or signals, **use a placeholder in the format `[PLACEHOLDER: <what's needed>]`** (e.g., `[PLACEHOLDER: customer reference]`, `[PLACEHOLDER: outcome metric]`, `[PLACEHOLDER: case study]`). Placeholders make the gap visible to the user; fabrication hides it.\n- **Email-1 personal touches come only from confirmed Lusha career history; padding is worse than nothing.** A personal touch in Email 1 may be drafted only from Lusha enrich data showing a confirmed prior employer (non-empty `previous_employment`, or a verified secondary email-domain that resolves to a known company) AND only when a specific, non-obvious, relevant insight can be drawn from it. Never personalize from weak proxies — city / region / \"scene\", company national origin, URL-handle or username trivia, phone area-code or country-code inference, or restating funding / headcount / news the recipient already knows — and never fabricate career history when the enrich data has no confirmed prior employer. When the gate does not pass, add no personal touch and use the standard persona-pain / signal-anchored opener. Personalization is Lusha-sourced only: a user-supplied custom signal (batch signal, CSV column, or uploaded file) is not a personalization source even if it contains career history. A personal touch may assert only the confirmed employer, the contact's confirmed title/role as enrich returns it, and that employer's widely-known business; never assert what the contact personally did or was responsible for there beyond the confirmed title — inventing a role-specific responsibility from a real employer is still padding. Scope: Email 1 only.\n- **Never invent a persona not in the brief.**\n- **Honour every brief `MISSING:` or `unconfirmed` marker.** Soften or omit dependent claims at draft time.\n- **State existing-account quota use before large harvests.** Estimate and confirm before signal harvest when the audience has more than 10 contacts (via `signal-prospect` conventions). Never suggest changing the user's account entitlement.\n- **Never run a web search silently.**\n- **Steps 5, 6, and 7 are REQUIRED before drafting.** After the brief and audience are loaded, you MUST ask Step 5 (signal preferences), Step 6 (common batch signal), and Step 7 (sample gate) in your first response — unless Step 5 was pre-answered by explicit skip authorization. Do not proceed to Step 8 until all three have been asked. Silence is not skip authorization.\n- **Step 5 is the contract — bi-directional.** Never harvest a signal type the user did not select. Never skip harvest entirely unless the user explicitly authorized skip (e.g., \"skip the signal harvest\", \"no signal harvest needed\", \"don't call MCP tools\"). Absence of signal direction is NOT skip authorization — ASK the user in your first response.\n- **Conditional output columns.** Never emit empty `email_2_*` / `linkedin_message_*` columns for undrafted messages.\n- **Iterate until the user is happy.** The post-draft menu is a loop, not a one-shot.\n- **No em-dashes in drafted recipient-facing copy.** Email subject lines, email bodies, LinkedIn connection requests, and LinkedIn DMs must NOT contain the em-dash character (— / U+2014). The em-dash is a recognized AI-writing signature and recipients pattern-match against it. Replace with appropriate alternatives based on the structural role:\n   - **After a greeting** (`Hey Sarah — when...`) → use a comma: `Hey Sarah, when...`\n   - **For asides / parentheticals** (`the data is in — and that's the gap`) → use a comma, period, or parentheses: `the data is in, and that's the gap` or `the data is in. That's the gap.`\n   - **For explanations / appositives** (`Acme Analytics — no Jira ticket required`) → use a colon, period, or hyphen: `Acme Analytics: no Jira ticket required` or `Acme Analytics. No Jira ticket required.`\n   - **For range or pause** → use a period or comma for pause; use a hyphen (-) for range.\n   - **Mandatory final scan:** before presenting any draft and before writing any file, scan every drafted subject and body in the batch — including bodies retained or carried over from an earlier turn, even for contacts you did not re-draft — for the `—` (U+2014) character, and apply the substitutions above to each occurrence. Do not state or self-certify em-dash compliance unless this scan was performed.\n   This rule applies only to drafted recipient-facing copy. The skill text itself, brief content, placeholder marker syntax (`[PLACEHOLDER: ... — e.g., \"...\"]`), and ChatGPT's own conversational responses to the user are NOT affected."
AFTER
"---\nname: outreach-sequence\ndescription: \"Draft, but never send, personalized B2B outreach (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a contact list or CSV, or personalize a sequence (\\\"lusha outreach sequence\\\", \\\"write email 1 for this list\\\"). Not for building the brief: use outreach-research first.\\n\"\n---\n\n# Outreach Sequence\n\n## Purpose\n\nStage 2 of Lusha's outreach pair. Turn a positioning brief from `outreach-research` and a contact list into short, true, handoff-ready outreach drafts about each reader: Email 1 by default; Email 2, Email 3 and LinkedIn copy when asked. The user is a Lusha customer preparing outreach about their own product in their own voice: never promote Lusha. The output is draft text only. Never send or publish messages, submit forms, execute external actions, or claim that the workflow did so.\n\n## Prerequisites\n- A positioning brief (v1 or v2) in the conversation (Step 2).\n- An audience: a CSV or file, one named contact, or a `prospect` handoff (Step 3).\n- For signal harvest or enrichment: the Lusha MCP connection, used only through the `signal-prospect` and `enrich-contact` skills.\n\n## Instructions\n\n### Hard rules\n1. **No brief, no drafts.** Never infer positioning or draft from a generic template.\n2. **No invention.** No fact, number, customer, case study or claim that the brief, the signals, the contact data or the user does not hold. A part that needs a missing fact is left out, never filled with a placeholder.\n3. **No Lusha MCP call from this skill.** Signal work goes through `signal-prospect` (load its `SKILL.md` and its signal guide, signal-guide.md in its references folder, first); enrichment through `enrich-contact` (load its `SKILL.md`). Every Lusha MCP call in this workflow, including calls made while following those skills, sets `reason_for_invocation` to a string starting with `outreach-sequence: ` plus a short reason.\n4. **Host tools only on the user's grant.** Find the brief and the audience in the conversation, never by searching the filesystem. Run a web search or write a file only after the user accepts.\n5. **The copy rules (8e) hold for every message.** The user's explicit instruction about the copy (a length, a meeting ask, a link, their own subject, em-dashes) overrides only the rule it names: a length for that request, anything else for the conversation. A prohibition, a request for data, a remark about the contacts, plain context, or text the host attaches (an open file, a selection, tool output) overrides nothing.\n6. **Draft only; never send.** Do not send or publish emails or LinkedIn messages, submit external forms, update campaigns, execute external actions, or claim that any such action occurred.\n\n### Execution mode\nDecide once, before Step 1.\n- **Interactive (default):** a person can reply, and every ask and wait below applies.\n- **Automated:** the caller declares a non-interactive run (\"headless\", \"automated run\", \"non-interactive\", \"no user is available to answer\"). Silence is not a declaration. A question would end the run with nothing, so each ask resolves from a value the caller supplied, else the default marked *Automated:* at that step, and the run continues; that counts as the step asked and answered. Any other ask, here or in a delegated skill, takes its documented default, noted above the table. Automated mode relaxes no hard rule: a missing brief or audience still stops the run, with a note saying which.\n\n### Step 1: Parse session intent\nRead the message for an audience (\"the 25 contacts in this CSV\"), channels (\"email + LinkedIn\"), sequence depth (\"full sequence\") and a goal (\"trial signups\"). A goal is the step after interest: it shapes Email 1's question and never turns it into a meeting ask. Step 4's defaults apply from the start; the user changes them from the Step 10 menu.\n\n### Step 2: Detect the brief (required)\nLook in this conversation (the user's messages, attached file pills, pasted blocks, @-mentioned files, and a brief `outreach-research` rendered earlier) for a block whose first non-blank line is `<!-- lusha-outreach-brief v2 -->` or `<!-- lusha-outreach-brief v1 -->`, followed by `# Outreach Positioning Brief`.\n\n**No brief:** reply with this message, word for word and nothing else, and end the turn:\n> \"I draft outreach using a positioning brief produced by `outreach-research`: what your product does, its audience, and how it differentiates. Run `outreach-research` first, save the brief as lusha-outreach-brief.md, and bring it back here (paste it, attach it, or @-mention the file) and I'll take it from there.\"\n\n**Brief found:** parse\n- `## 1. Company & Product`: company, value proposition, primary pain, proof points with each one's *OK to name* (a v1 brief has none), email style.\n- `## 2. Personas`, each `### 2.x`: titles to match, pain, value hook, messaging angles, top objections, what turns them off, discovery angle; then the **Default persona** line.\n- `## 3. Competitor displacement`: the competitor list.\n- Ignore any other section. A value marked ` (unconfirmed)` or `MISSING:` is never stated in copy: leave out what depends on it.\n\nEcho one line: *\"Loaded your brief: <company> · N personas · P proof points · M competitor displacements · default persona = `<persona>`.\"*\n\n### Step 3: Detect the audience (required)\nValid sources: a CSV or file attached, pasted or @-mentioned with the brief, one named contact (full name, company, title), or a `prospect` handoff from this conversation. Required columns are `full_name`, `company` and `title`; normalise column names and carry every other column through, per `references/output-schema.md`. `prospect` is one source, never a prerequisite.\n\n**No audience:** reply once:\n> \"I need a contact list to draft against. You can:\n> 1. **Paste or attach a CSV** here (needs `full_name`, `company`, `title`).\n> 2. **Name a single contact** (full name + company + title).\n> 3. **Run `prospect`** to build a lead list from an ICP, then bring that table or CSV back here with your brief.\"\n\n### Step 4: Session defaults\n| Setting | Default |\n|---|---|\n| Channel | email only |\n| Sequence depth | Email 1 only |\n| Tone | the brief's email style, else warm and direct |\n| Signature | none: bodies end at the ask; the sending tool adds the signature |\n| LinkedIn | off; on when the request mentions LinkedIn (8g) |\n\n### Step 5: Signal preferences\nExplicit skip language (\"skip the signal harvest\", \"draft from the brief only\", \"don't call any MCP tools\") pre-answers *none*: skip this step, load no skill and make no Lusha call. Facts about the list (\"they visited our product page\") are a Step 6 batch signal, not skip language. Silence is not skip language either.\n\nOtherwise load `signal-prospect` and follow its Step 2 (discover company and contact signal types) and Step 3 (map intent to ids validated against the live response, with the most specific sub-filter from its signal guide). Never invent a signal id, and never run its Step 4 or Steps 6–8, which find and enrich new people. Then ask which signal families to harvest, with the families from the live response inside the question sentence and \"all\" or \"none\" at its end. When the answer excludes or adds something (\"funding, but not IPOs\"), read the resulting list back in one line before harvesting.\n- **all:** every family; company-side and contact-side search for every contact.\n- **specific families:** only those, on the endpoints that carry them.\n- **none:** no harvest; draft from the brief, the batch signal and any signals in the CSV.\n\n*Automated:* the supplied value, else **all**.\n\n### Step 6: Batch signal\nAsk once: *\"Is there a signal that's already true for every contact on this list, something you know I should weave into every draft? If nothing applies, say none.\"* Offer a web search only to ground context the user describes. *Automated:* the supplied value, else none.\n\n### Step 7: Sample gate\nAsk once: *\"Want a sample gate? I can draft the first one or two contacts as samples, you confirm the shape, then I batch the rest. How many samples?\"* Default: no gate. With a gate, draft the samples, pause, then apply the confirmed edits to the rest. *Automated:* no gate.\n\n**Interactive:** ask Steps 5, 6 and 7 together in the first reply after the brief and audience load (Step 5 only when not pre-answered), and draft nothing until they are answered.\n\n### Step 8: Per-contact pipeline\n\n#### 8a. Persona\n1. `persona_override` in the row: use it as given.\n2. Else an exact, case-insensitive match of the title against a persona's *Titles to match*.\n3. Else the closest persona by pain and titles; when still unsure, the **Default persona**. Never invent a persona.\n\n#### 8b. Signal harvest (not on *none*)\nUse `signal-prospect`'s Step 5 lookup by identifier (`signals_companies_search`, `signals_contacts_search`; up to 25 per call), with `startDate` 90 days back and `maxResultsPerSignal` 3. Request by id only the chosen types that can be a reason (8c), never `allSignals`; *all* means `surgeInHiringByDepartment` (the persona's departments), `productActivityNews`, `peopleNews`, `financialEventsNews`, `commercialActivityNews`, `corporateStrategyNews`, `riskNews`, `marketIntelligenceNews`, and `promotion`, `companyChange` for contacts. Each signal returned uses quota already included in the user's existing Lusha account: before the first call, state the upper bound of existing-account quota use (contacts × types × 3), and that this workflow cannot change the user's account entitlement; with more than 10 contacts, wait for confirmation. *Automated:* state it and proceed. If a call reports that the existing entitlement is insufficient, say so, stop the harvest, name the failing call and ask: skip the rest, or draft with what was harvested. Never suggest changing the user's account entitlement. *Automated:* draft with what was harvested, and say so.\n\n#### 8b.5. Competitor conflict (once per batch)\nWhen `## 3` is empty and a harvested signal, a CSV signal or the batch signal that can appear in a message (not a timing-only item, 8c) names a company positioned as an alternative to the user's product, ask once: name it, reference the activity without the name, or skip that signal. Apply the answer to every affected draft. *Automated:* reference it without the name, and say so. A competitor listed in `## 3`, or one the user chose here to name, is named only when a signal shows this prospect uses or evaluates it; no other company is ever named as a competitor.\n\n#### 8c. Signals in the copy\nA signal can be a message's reason for writing only when all of these hold:\n- **Relevant:** this persona's pain in the brief follows from it without an assumption. Hiring qualifies as a rise above its usual level in the contact's own function (the department this persona works in or leads); a single job post, or company-wide hiring, does not. A launch that uses what the user's product does, or a new leader in the persona's function, qualifies. Hiring in another department, headcount growth, or a property or plant investment helps pick whom to write to; it is never the reason.\n- **Fresh:** dated within 90 days of today. Under about two weeks old, it can be the hook; from two weeks to 90 days, name it once and ask about its consequence. An older signal never appears in a message.\n- **Stated as the source states it:** the month or the event, never relative time. No percentage change; a count only with its baseline, as given; otherwise describe the change without a figure and without inflating it. Hiring is open roles, never headcount or team growth.\n- **Observed, then asked:** state the fact, then ask. Never describe what is happening inside the prospect's team, or bridge the signal to a claim about their workload.\n\nWebsite visits, intent topics, estimated figures (IT spend, website traffic) and undated items (a fit score, a score reason) are timing-only: they set the timing or the angle, never appear in a message and are never the reason. A first-hand fact the user stated (where they met, a referral, the batch signal) is used as stated, unless it is tracking-type: then it only sets the timing. Altitude: for directors and above, prefer a company-level reason; for managers and individual contributors, one about the person.\n\nEach contact's reason, in order: a first-hand fact; a signal that passes; otherwise the persona's pain, with one real detail about this contact or their company (8f).\n\n#### 8d. Personal touch\nAllowed only when this contact's Lusha enrich result is in hand and shows a prior employer other than the current one. It is one clause, stated plainly as a fact about them (never as something you looked up): the prior employer and, when enrich gives one, the prior title, exactly as enrich gives them, and nothing about either: nothing about what that employer does or is known for, and nothing about what the person built, owned, saw, thinks or is good at. A touch that passes goes in Email 1. No enrich result, or no prior employer: no touch. Never personalize from location, company origin, a handle or username, a phone prefix, restated news, or the obvious about their role.\n\nThe enrich result is enrich data already in the conversation (an `enrich-contact` card, an attached enrich export, a `prospect` handoff with enrich fields), used directly, or it is fetched through `enrich-contact`'s preview-then-reveal path (its Steps 1–2): look the contact up with `enrich: false`; only when the preview lists `previousEmployment`, reveal emails alone, Lusha-only (no waterfall), to read it. A result at another company is not this contact. Never its signal check, contact card or next-action steps; then return here. Before the first lookup, state the estimated use of quota already included in the user's existing Lusha account: one lookup per contact, plus the email reveals. This workflow cannot change the user's account entitlement. Interactive: fetch only after the user picks **Add personalization** in the Step 10 menu, never during the first draft. *Automated:* fetch for every contact during the draft, unless the caller declined enrichment. `enrich-contact` owns its existing-account quota handling. Career history the user supplied is a first-hand fact, not a personal touch.\n\n#### 8e. Copy rules (every message)\n- No placeholders: no brackets, braces or TBD. A part whose fact the brief lacks is left out.\n- No em-dash character. Replace each by its role: a comma after a greeting, a comma or parentheses for an aside, a colon for an explanation, a hyphen for a range. Before presenting or saving drafts, scan every subject and body, including ones kept from earlier turns, and fix any you find.\n- No relative time anywhere, the ask included, not even \"today\" or \"recently\": name the month or the event.\n- No sentence invites a meeting, asked or stated: no call, meeting, demo, chat, calendar link, time slot or minutes of their time. \"Call\" in a statement about the product is fine. No question is built on \"worth\".\n- No compliments, congratulations, intensifiers or hype: state facts plainly. Nothing about how the reader thinks or feels.\n- No subject starts with \"Re:\" or \"Fwd:\". No links or tracking unless the user asks for a link.\n- Write each contact's copy for that contact: no subject, and no message's first sentence, repeated word for word across the batch.\n- An email body is one short paragraph after the greeting (the question may stand on its own line), never one sentence per line.\n\n#### 8f. Email 1\nEvery email opens with *Hi {first name},* on its own line. Then five short parts, in this order, 50–90 words in the body (greeting excluded), never over 100:\n1. **Why now** (8c's reason): a first-hand fact as the user stated it; or what a qualifying signal means for someone in this reader's role, said about the role, not as a claim about their team, with the event itself named at most once and never in the first sentence; or, when the reason is the persona's pain, parts 1 and 2 as one sentence.\n2. **Pain:** one sentence, in the brief's words for this persona. A personal touch (8d) is its own short sentence right after part 1. Without one, part 1 or 2 names one real detail about this contact or their company (their title or team; the company's size, industry or technology), as the data gives it, never what it suggests about them.\n3. **What it does:** one sentence from the persona's value hook, without adjectives or promotional words.\n4. **Proof:** one proof point from the brief that fits this persona or industry, naming the customer only when marked *OK to name: yes*. Left out when none fits.\n5. **Ask:** one question, the email's only question: interest in the problem, or an offer of something useful. The persona's discovery angle can shape it.\n\nSubject: 3–5 words, never over 6, naming the reason or the pain. Honour the 8b.5 choice and the persona's turn-offs.\n\n#### 8g. Email 2, Email 3 and LinkedIn\nOnly when asked, up front or from the menu: read `references/message-shapes.md` and follow its shapes. LinkedIn copy means the message for once they accept, unless the user asks for connection notes.\n\n### Step 9: Render the output\nRender the drafts inline as a Markdown table: `full_name`, `company`, `title`, each drafted message, then `hook_source` and `personal_touch_source` on every row. The full CSV (every input column plus the generated ones, per `references/output-schema.md`) comes from the menu's save item. *Automated:* emit the full CSV in a `csv` code block instead of the table, or write it where the caller asked. Above the drafts, once: any Automated defaults applied, and the LinkedIn batch line when it applies, word for word, as its own line. Below it: contacts drafted, whether the harvest ran, existing-account quota used; then one line naming what the brief is missing and which drafts it would improve (for example: no proof points, so no Email 2 cites proof).\n\n### Step 10: Post-draft menu\nInteractive only. End with a numbered menu of the items that fit the session: add a sign-off; change channel; change tone; add LinkedIn connection notes; expand to the full sequence; regenerate; save to a file; add personalization (Lusha enrich). When the user picks one, read `references/post-draft-menu.md` and follow it; loop until the user is satisfied. *Automated:* skip; a caller that wants an item's effect asks for it up front.\n\n### Before you reply\nCheck every draft against this list, rewrite any that fails, and check it again. An item the user's own instruction overrides (hard rule 5) is checked against that instruction instead.\n1. Email 1's first sentence is a first-hand fact or about the reader's role, never the Lusha event; a pain-led Email 1 names one real detail about the contact or their company.\n2. Every email opens with *Hi {first name},*. No subject, and no message's first sentence, is shared with another contact.\n3. No placeholder, em-dash, relative time, percentage taken from a signal, or meeting ask the user did not request; no figure in LinkedIn copy.\n4. Lengths: Email 1 50–90 words, Email 2 40–80, Email 3 25–50, each shorter than the one before, except where a length the user set changes them (`references/message-shapes.md`); LinkedIn message under 400 characters, note at most 200.\n5. Each signal and proof point matches its source; a personal touch says nothing beyond the prior title and employer.\n\n## Examples\n- Brief and CSV in one message, *\"draft email 1 for these\"* → Steps 5–7 asked together; then harvest, drafts, table.\n- *\"Skip the signal harvest and draft from the brief only\"* → Steps 6 and 7 asked; no Lusha call.\n- An automated full-sequence run with LinkedIn → no questions; Emails 1–3 and a LinkedIn message per contact.\n- No brief in the conversation → the Step 2 refusal, and nothing else.\n\n## Limitations\n- Drafts only: never sends email or LinkedIn messages, or pushes to a sequencer or CRM.\n- Copy is only as specific as the brief and the signals.\n\n## Troubleshooting\n- **A delegated skill cannot be loaded:** say so. Without `signal-prospect`, treat Step 5 as *none*; without `enrich-contact`, add no personal touch.\n- **A CSV lacks a required column:** name it and ask for it. *Automated:* draft the rows that have all three and list the rest.\n- **Existing entitlement insufficient:** see 8b.\n"
Full snapshot data
{
  "description": "Draft, but never send, personalized B2B outreach (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a contact list or CSV, or personalize a sequence (\"lusha outreach sequence\", \"write email 1 for this list\"). Not for building the brief: use outreach-research first.\n",
  "included_files": [
    {
      "relative_path": "references/message-shapes.md",
      "size_in_bytes": 3899
    },
    {
      "relative_path": "references/output-schema.md",
      "size_in_bytes": 2739
    },
    {
      "relative_path": "references/post-draft-menu.md",
      "size_in_bytes": 2032
    }
  ],
  "name": "outreach-sequence",
  "skill_md_contents": "---\nname: outreach-sequence\ndescription: \"Draft, but never send, personalized B2B outreach (Email 1, optional Email 2 and 3, and LinkedIn copy) for contacts the user already has, from an outreach-research positioning brief plus Lusha buying signals. Use when asked to draft outreach, write emails or LinkedIn messages for a contact list or CSV, or personalize a sequence (\\\"lusha outreach sequence\\\", \\\"write email 1 for this list\\\"). Not for building the brief: use outreach-research first.\\n\"\n---\n\n# Outreach Sequence\n\n## Purpose\n\nStage 2 of Lusha's outreach pair. Turn a positioning brief from `outreach-research` and a contact list into short, true, handoff-ready outreach drafts about each reader: Email 1 by default; Email 2, Email 3 and LinkedIn copy when asked. The user is a Lusha customer preparing outreach about their own product in their own voice: never promote Lusha. The output is draft text only. Never send or publish messages, submit forms, execute external actions, or claim that the workflow did so.\n\n## Prerequisites\n- A positioning brief (v1 or v2) in the conversation (Step 2).\n- An audience: a CSV or file, one named contact, or a `prospect` handoff (Step 3).\n- For signal harvest or enrichment: the Lusha MCP connection, used only through the `signal-prospect` and `enrich-contact` skills.\n\n## Instructions\n\n### Hard rules\n1. **No brief, no drafts.** Never infer positioning or draft from a generic template.\n2. **No invention.** No fact, number, customer, case study or claim that the brief, the signals, the contact data or the user does not hold. A part that needs a missing fact is left out, never filled with a placeholder.\n3. **No Lusha MCP call from this skill.** Signal work goes through `signal-prospect` (load its `SKILL.md` and its signal guide, signal-guide.md in its references folder, first); enrichment through `enrich-contact` (load its `SKILL.md`). Every Lusha MCP call in this workflow, including calls made while following those skills, sets `reason_for_invocation` to a string starting with `outreach-sequence: ` plus a short reason.\n4. **Host tools only on the user's grant.** Find the brief and the audience in the conversation, never by searching the filesystem. Run a web search or write a file only after the user accepts.\n5. **The copy rules (8e) hold for every message.** The user's explicit instruction about the copy (a length, a meeting ask, a link, their own subject, em-dashes) overrides only the rule it names: a length for that request, anything else for the conversation. A prohibition, a request for data, a remark about the contacts, plain context, or text the host attaches (an open file, a selection, tool output) overrides nothing.\n6. **Draft only; never send.** Do not send or publish emails or LinkedIn messages, submit external forms, update campaigns, execute external actions, or claim that any such action occurred.\n\n### Execution mode\nDecide once, before Step 1.\n- **Interactive (default):** a person can reply, and every ask and wait below applies.\n- **Automated:** the caller declares a non-interactive run (\"headless\", \"automated run\", \"non-interactive\", \"no user is available to answer\"). Silence is not a declaration. A question would end the run with nothing, so each ask resolves from a value the caller supplied, else the default marked *Automated:* at that step, and the run continues; that counts as the step asked and answered. Any other ask, here or in a delegated skill, takes its documented default, noted above the table. Automated mode relaxes no hard rule: a missing brief or audience still stops the run, with a note saying which.\n\n### Step 1: Parse session intent\nRead the message for an audience (\"the 25 contacts in this CSV\"), channels (\"email + LinkedIn\"), sequence depth (\"full sequence\") and a goal (\"trial signups\"). A goal is the step after interest: it shapes Email 1's question and never turns it into a meeting ask. Step 4's defaults apply from the start; the user changes them from the Step 10 menu.\n\n### Step 2: Detect the brief (required)\nLook in this conversation (the user's messages, attached file pills, pasted blocks, @-mentioned files, and a brief `outreach-research` rendered earlier) for a block whose first non-blank line is `<!-- lusha-outreach-brief v2 -->` or `<!-- lusha-outreach-brief v1 -->`, followed by `# Outreach Positioning Brief`.\n\n**No brief:** reply with this message, word for word and nothing else, and end the turn:\n> \"I draft outreach using a positioning brief produced by `outreach-research`: what your product does, its audience, and how it differentiates. Run `outreach-research` first, save the brief as lusha-outreach-brief.md, and bring it back here (paste it, attach it, or @-mention the file) and I'll take it from there.\"\n\n**Brief found:** parse\n- `## 1. Company & Product`: company, value proposition, primary pain, proof points with each one's *OK to name* (a v1 brief has none), email style.\n- `## 2. Personas`, each `### 2.x`: titles to match, pain, value hook, messaging angles, top objections, what turns them off, discovery angle; then the **Default persona** line.\n- `## 3. Competitor displacement`: the competitor list.\n- Ignore any other section. A value marked ` (unconfirmed)` or `MISSING:` is never stated in copy: leave out what depends on it.\n\nEcho one line: *\"Loaded your brief: <company> · N personas · P proof points · M competitor displacements · default persona = `<persona>`.\"*\n\n### Step 3: Detect the audience (required)\nValid sources: a CSV or file attached, pasted or @-mentioned with the brief, one named contact (full name, company, title), or a `prospect` handoff from this conversation. Required columns are `full_name`, `company` and `title`; normalise column names and carry every other column through, per `references/output-schema.md`. `prospect` is one source, never a prerequisite.\n\n**No audience:** reply once:\n> \"I need a contact list to draft against. You can:\n> 1. **Paste or attach a CSV** here (needs `full_name`, `company`, `title`).\n> 2. **Name a single contact** (full name + company + title).\n> 3. **Run `prospect`** to build a lead list from an ICP, then bring that table or CSV back here with your brief.\"\n\n### Step 4: Session defaults\n| Setting | Default |\n|---|---|\n| Channel | email only |\n| Sequence depth | Email 1 only |\n| Tone | the brief's email style, else warm and direct |\n| Signature | none: bodies end at the ask; the sending tool adds the signature |\n| LinkedIn | off; on when the request mentions LinkedIn (8g) |\n\n### Step 5: Signal preferences\nExplicit skip language (\"skip the signal harvest\", \"draft from the brief only\", \"don't call any MCP tools\") pre-answers *none*: skip this step, load no skill and make no Lusha call. Facts about the list (\"they visited our product page\") are a Step 6 batch signal, not skip language. Silence is not skip language either.\n\nOtherwise load `signal-prospect` and follow its Step 2 (discover company and contact signal types) and Step 3 (map intent to ids validated against the live response, with the most specific sub-filter from its signal guide). Never invent a signal id, and never run its Step 4 or Steps 6–8, which find and enrich new people. Then ask which signal families to harvest, with the families from the live response inside the question sentence and \"all\" or \"none\" at its end. When the answer excludes or adds something (\"funding, but not IPOs\"), read the resulting list back in one line before harvesting.\n- **all:** every family; company-side and contact-side search for every contact.\n- **specific families:** only those, on the endpoints that carry them.\n- **none:** no harvest; draft from the brief, the batch signal and any signals in the CSV.\n\n*Automated:* the supplied value, else **all**.\n\n### Step 6: Batch signal\nAsk once: *\"Is there a signal that's already true for every contact on this list, something you know I should weave into every draft? If nothing applies, say none.\"* Offer a web search only to ground context the user describes. *Automated:* the supplied value, else none.\n\n### Step 7: Sample gate\nAsk once: *\"Want a sample gate? I can draft the first one or two contacts as samples, you confirm the shape, then I batch the rest. How many samples?\"* Default: no gate. With a gate, draft the samples, pause, then apply the confirmed edits to the rest. *Automated:* no gate.\n\n**Interactive:** ask Steps 5, 6 and 7 together in the first reply after the brief and audience load (Step 5 only when not pre-answered), and draft nothing until they are answered.\n\n### Step 8: Per-contact pipeline\n\n#### 8a. Persona\n1. `persona_override` in the row: use it as given.\n2. Else an exact, case-insensitive match of the title against a persona's *Titles to match*.\n3. Else the closest persona by pain and titles; when still unsure, the **Default persona**. Never invent a persona.\n\n#### 8b. Signal harvest (not on *none*)\nUse `signal-prospect`'s Step 5 lookup by identifier (`signals_companies_search`, `signals_contacts_search`; up to 25 per call), with `startDate` 90 days back and `maxResultsPerSignal` 3. Request by id only the chosen types that can be a reason (8c), never `allSignals`; *all* means `surgeInHiringByDepartment` (the persona's departments), `productActivityNews`, `peopleNews`, `financialEventsNews`, `commercialActivityNews`, `corporateStrategyNews`, `riskNews`, `marketIntelligenceNews`, and `promotion`, `companyChange` for contacts. Each signal returned uses quota already included in the user's existing Lusha account: before the first call, state the upper bound of existing-account quota use (contacts × types × 3), and that this workflow cannot change the user's account entitlement; with more than 10 contacts, wait for confirmation. *Automated:* state it and proceed. If a call reports that the existing entitlement is insufficient, say so, stop the harvest, name the failing call and ask: skip the rest, or draft with what was harvested. Never suggest changing the user's account entitlement. *Automated:* draft with what was harvested, and say so.\n\n#### 8b.5. Competitor conflict (once per batch)\nWhen `## 3` is empty and a harvested signal, a CSV signal or the batch signal that can appear in a message (not a timing-only item, 8c) names a company positioned as an alternative to the user's product, ask once: name it, reference the activity without the name, or skip that signal. Apply the answer to every affected draft. *Automated:* reference it without the name, and say so. A competitor listed in `## 3`, or one the user chose here to name, is named only when a signal shows this prospect uses or evaluates it; no other company is ever named as a competitor.\n\n#### 8c. Signals in the copy\nA signal can be a message's reason for writing only when all of these hold:\n- **Relevant:** this persona's pain in the brief follows from it without an assumption. Hiring qualifies as a rise above its usual level in the contact's own function (the department this persona works in or leads); a single job post, or company-wide hiring, does not. A launch that uses what the user's product does, or a new leader in the persona's function, qualifies. Hiring in another department, headcount growth, or a property or plant investment helps pick whom to write to; it is never the reason.\n- **Fresh:** dated within 90 days of today. Under about two weeks old, it can be the hook; from two weeks to 90 days, name it once and ask about its consequence. An older signal never appears in a message.\n- **Stated as the source states it:** the month or the event, never relative time. No percentage change; a count only with its baseline, as given; otherwise describe the change without a figure and without inflating it. Hiring is open roles, never headcount or team growth.\n- **Observed, then asked:** state the fact, then ask. Never describe what is happening inside the prospect's team, or bridge the signal to a claim about their workload.\n\nWebsite visits, intent topics, estimated figures (IT spend, website traffic) and undated items (a fit score, a score reason) are timing-only: they set the timing or the angle, never appear in a message and are never the reason. A first-hand fact the user stated (where they met, a referral, the batch signal) is used as stated, unless it is tracking-type: then it only sets the timing. Altitude: for directors and above, prefer a company-level reason; for managers and individual contributors, one about the person.\n\nEach contact's reason, in order: a first-hand fact; a signal that passes; otherwise the persona's pain, with one real detail about this contact or their company (8f).\n\n#### 8d. Personal touch\nAllowed only when this contact's Lusha enrich result is in hand and shows a prior employer other than the current one. It is one clause, stated plainly as a fact about them (never as something you looked up): the prior employer and, when enrich gives one, the prior title, exactly as enrich gives them, and nothing about either: nothing about what that employer does or is known for, and nothing about what the person built, owned, saw, thinks or is good at. A touch that passes goes in Email 1. No enrich result, or no prior employer: no touch. Never personalize from location, company origin, a handle or username, a phone prefix, restated news, or the obvious about their role.\n\nThe enrich result is enrich data already in the conversation (an `enrich-contact` card, an attached enrich export, a `prospect` handoff with enrich fields), used directly, or it is fetched through `enrich-contact`'s preview-then-reveal path (its Steps 1–2): look the contact up with `enrich: false`; only when the preview lists `previousEmployment`, reveal emails alone, Lusha-only (no waterfall), to read it. A result at another company is not this contact. Never its signal check, contact card or next-action steps; then return here. Before the first lookup, state the estimated use of quota already included in the user's existing Lusha account: one lookup per contact, plus the email reveals. This workflow cannot change the user's account entitlement. Interactive: fetch only after the user picks **Add personalization** in the Step 10 menu, never during the first draft. *Automated:* fetch for every contact during the draft, unless the caller declined enrichment. `enrich-contact` owns its existing-account quota handling. Career history the user supplied is a first-hand fact, not a personal touch.\n\n#### 8e. Copy rules (every message)\n- No placeholders: no brackets, braces or TBD. A part whose fact the brief lacks is left out.\n- No em-dash character. Replace each by its role: a comma after a greeting, a comma or parentheses for an aside, a colon for an explanation, a hyphen for a range. Before presenting or saving drafts, scan every subject and body, including ones kept from earlier turns, and fix any you find.\n- No relative time anywhere, the ask included, not even \"today\" or \"recently\": name the month or the event.\n- No sentence invites a meeting, asked or stated: no call, meeting, demo, chat, calendar link, time slot or minutes of their time. \"Call\" in a statement about the product is fine. No question is built on \"worth\".\n- No compliments, congratulations, intensifiers or hype: state facts plainly. Nothing about how the reader thinks or feels.\n- No subject starts with \"Re:\" or \"Fwd:\". No links or tracking unless the user asks for a link.\n- Write each contact's copy for that contact: no subject, and no message's first sentence, repeated word for word across the batch.\n- An email body is one short paragraph after the greeting (the question may stand on its own line), never one sentence per line.\n\n#### 8f. Email 1\nEvery email opens with *Hi {first name},* on its own line. Then five short parts, in this order, 50–90 words in the body (greeting excluded), never over 100:\n1. **Why now** (8c's reason): a first-hand fact as the user stated it; or what a qualifying signal means for someone in this reader's role, said about the role, not as a claim about their team, with the event itself named at most once and never in the first sentence; or, when the reason is the persona's pain, parts 1 and 2 as one sentence.\n2. **Pain:** one sentence, in the brief's words for this persona. A personal touch (8d) is its own short sentence right after part 1. Without one, part 1 or 2 names one real detail about this contact or their company (their title or team; the company's size, industry or technology), as the data gives it, never what it suggests about them.\n3. **What it does:** one sentence from the persona's value hook, without adjectives or promotional words.\n4. **Proof:** one proof point from the brief that fits this persona or industry, naming the customer only when marked *OK to name: yes*. Left out when none fits.\n5. **Ask:** one question, the email's only question: interest in the problem, or an offer of something useful. The persona's discovery angle can shape it.\n\nSubject: 3–5 words, never over 6, naming the reason or the pain. Honour the 8b.5 choice and the persona's turn-offs.\n\n#### 8g. Email 2, Email 3 and LinkedIn\nOnly when asked, up front or from the menu: read `references/message-shapes.md` and follow its shapes. LinkedIn copy means the message for once they accept, unless the user asks for connection notes.\n\n### Step 9: Render the output\nRender the drafts inline as a Markdown table: `full_name`, `company`, `title`, each drafted message, then `hook_source` and `personal_touch_source` on every row. The full CSV (every input column plus the generated ones, per `references/output-schema.md`) comes from the menu's save item. *Automated:* emit the full CSV in a `csv` code block instead of the table, or write it where the caller asked. Above the drafts, once: any Automated defaults applied, and the LinkedIn batch line when it applies, word for word, as its own line. Below it: contacts drafted, whether the harvest ran, existing-account quota used; then one line naming what the brief is missing and which drafts it would improve (for example: no proof points, so no Email 2 cites proof).\n\n### Step 10: Post-draft menu\nInteractive only. End with a numbered menu of the items that fit the session: add a sign-off; change channel; change tone; add LinkedIn connection notes; expand to the full sequence; regenerate; save to a file; add personalization (Lusha enrich). When the user picks one, read `references/post-draft-menu.md` and follow it; loop until the user is satisfied. *Automated:* skip; a caller that wants an item's effect asks for it up front.\n\n### Before you reply\nCheck every draft against this list, rewrite any that fails, and check it again. An item the user's own instruction overrides (hard rule 5) is checked against that instruction instead.\n1. Email 1's first sentence is a first-hand fact or about the reader's role, never the Lusha event; a pain-led Email 1 names one real detail about the contact or their company.\n2. Every email opens with *Hi {first name},*. No subject, and no message's first sentence, is shared with another contact.\n3. No placeholder, em-dash, relative time, percentage taken from a signal, or meeting ask the user did not request; no figure in LinkedIn copy.\n4. Lengths: Email 1 50–90 words, Email 2 40–80, Email 3 25–50, each shorter than the one before, except where a length the user set changes them (`references/message-shapes.md`); LinkedIn message under 400 characters, note at most 200.\n5. Each signal and proof point matches its source; a personal touch says nothing beyond the prior title and employer.\n\n## Examples\n- Brief and CSV in one message, *\"draft email 1 for these\"* → Steps 5–7 asked together; then harvest, drafts, table.\n- *\"Skip the signal harvest and draft from the brief only\"* → Steps 6 and 7 asked; no Lusha call.\n- An automated full-sequence run with LinkedIn → no questions; Emails 1–3 and a LinkedIn message per contact.\n- No brief in the conversation → the Step 2 refusal, and nothing else.\n\n## Limitations\n- Drafts only: never sends email or LinkedIn messages, or pushes to a sequencer or CRM.\n- Copy is only as specific as the brief and the signals.\n\n## Troubleshooting\n- **A delegated skill cannot be loaded:** say so. Without `signal-prospect`, treat Step 5 as *none*; without `enrich-contact`, add no personal touch.\n- **A CSV lacks a required column:** name it and ask for it. *Automated:* draft the rows that have all three and list the rest.\n- **Existing entitlement insufficient:** see 8b.\n"
}

SHA-256 of public snapshot: d448790cf976538288ae3caa66ea74c2528c95980e1e022390cd591afdb2f6c1