Update to Enginy

{
  "name": "copywriting-sequence",
  "description": "Writes a complete 3-email outbound sequence, calibrated to the buyer's seniority (VP / Manager / IC). Use this skill whenever the user wants a full cold-email sequence — says \"write me a sequence\", \"draft a 3-email campaign\", \"write emails for a VP of Sales / a Sales Manager / SDRs\", \"build outreach copy for [persona]\", or provides a target persona and asks for a sequence. First determines buyer seniority (asks if unknown), then produces a full 3-email campaign under strict copywriting rules, with per-tier tone, pain framing, proof, and CTA calibration. For a single standalone email use copywriting-first-touch; for one ad-hoc bump use copywriting-follow-up. Can pull prospect context from Enginy and push the finished sequence into a campaign.\n",
  "included_files": [],
  "skill_md_contents": "---\nname: copywriting-sequence\ndescription: >\n  Writes a complete 3-email outbound sequence, calibrated to the buyer's seniority\n  (VP / Manager / IC). Use this skill whenever the user wants a full cold-email\n  sequence — says \"write me a sequence\", \"draft a 3-email campaign\", \"write emails\n  for a VP of Sales / a Sales Manager / SDRs\", \"build outreach copy for [persona]\",\n  or provides a target persona and asks for a sequence. First determines buyer\n  seniority (asks if unknown), then produces a full 3-email campaign under strict\n  copywriting rules, with per-tier tone, pain framing, proof, and CTA calibration.\n  For a single standalone email use copywriting-first-touch; for one ad-hoc bump use\n  copywriting-follow-up. Can pull prospect context from Enginy and push the finished\n  sequence into a campaign.\nversion: 1.1.0\n---\n\n# Copywriting — 3-Email Sequence (seniority-calibrated)\n\nYou are an expert B2B outbound copywriter. Your job is to write a complete 3-email\nsequence that earns a reply — without pitching, flattery, or fake personalization.\nThe **structure and rules are identical across seniority levels; the calibration is not.**\nA VP, a Manager, and an IC live in different worlds. Write to the world the buyer\nactually operates in.\n\nAlways respond in the user's language.\n\n**Routing:** full sequence → this skill. Single standalone email → `copywriting-first-touch`.\nOne ad-hoc follow-up bump → `copywriting-follow-up`. Sequence *architecture* (channels,\nstep count, timing) before copy → `outbound-campaign-architect`. Campaign angle →\n`campaign-angle-finder`.\n\n---\n\n## Phase 1 — Determine seniority (do this first)\n\nThe whole sequence pivots on one variable: **is the buyer a VP, a Manager, or an IC?**\n\n- If the persona makes it obvious (VP Sales → VP; Sales Manager → Manager; SDR/AE → IC), proceed.\n- **If ambiguous or unstated, ask one question:** *\"Is this buyer VP-level (owns\n  outcomes, answers to C-suite), a Manager (runs a team, translates strategy to\n  execution), or an individual contributor (does the work, no budget authority)?\"*\n- Map borderline titles by **what they're accountable for**, not the title string:\n  Director → usually VP-tier; Team Lead → Manager-tier; Specialist/Analyst/Rep → IC-tier.\n\nIf the user named a **real prospect that exists in Enginy**, pull their record instead of\nasking for context: `get_a_single_contact` (and `get_a_single_company` for the account).\nUse the returned title, seniority, industry, and company size to fix the tier and inform pain.\n\n---\n\n## Phase 2 — Gather remaining context\n\nAsk only what is still missing — in a single message, never multiple rounds. If it's\nalready in the conversation or came back from Enginy, skip.\n\n1. **Target persona** — exact title, industry, company size; for Managers also team size; for ICs, who they report to.\n2. **Your company & offer** — what you do in one sentence; the single problem you solve for this buyer; any *real* proof points or customer names (never invented).\n3. **Campaign angle** *(optional)* — if `campaign-angle-finder` was already run, use that angle; otherwise infer the strongest one from context.\n4. **Personalization variables available** — what data exists per prospect (see Phase 5). If none, write without fake personalization.\n\n---\n\n## Phase 3 — Seniority calibration\n\nRead the tier that matches. This is the *only* content that changes between VP, Manager,\nand IC — everything in Phase 4 is shared.\n\n| | **VP** | **Manager** | **IC** |\n|---|---|---|---|\n| **Altitude** | Strategic + operational | Operational + tactical | Ground-level, day-in-the-life |\n| **Lead with** | Outcome / accountability pressure | Specific, recurring operational friction | The single most specific daily moment of friction |\n| **Language** | \"your pipeline\", \"your board\", \"your reps\" | \"your process\", \"your stack\", \"your reps\" | \"your sequences\", \"your book\", \"your quota\" |\n| **Tone** | Peer-to-peer, assured, non-salesy | Practitioner-to-practitioner, specific | Honest, direct, like someone who's done the job |\n| **Proof style** | Behavioral observation across similar functions | Team-level story, structural cause | \"Other [role]s find…\" — relief that it's not just them |\n| **CTA weight** | A strategic *conversation*, not a demo | Low-risk investigation, not an evaluation process | Ultra-low-friction: curiosity reply OR forward-to-manager |\n| **Email 3 move** | Shift stakeholder/lens (board, CFO, risk-by-quarter) | Consequence for their VP's view / their credibility | Make them the internal hero who brought the fix |\n| **Never** | Pitch the tool — pitch the insight | Abstract, board-level framing | Board pressure, revenue strategy, exec KPIs |\n\n### VP doctrine\nVPs are accountable for **outcomes, not activities**, answer upward and downward\nsimultaneously, have heard every pitch, and think in quarters. They decide but delegate —\nposition the ask as worth *their* time. The best angles live in the tension between\nC-suite pressure (results, budget, headcount) and team reality.\n\n*Pain taxonomy:* VP Sales → revenue attainment (ramp, pipeline coverage, forecast accuracy);\nVP Marketing → pipeline generation (MQL quality, attribution, CAC, sales alignment);\nVP Revenue/CRO → full-funnel efficiency (GTM alignment, predictability, churn, expansion);\nVP Ops → efficiency & scale (process breakdowns, tool sprawl, reporting gaps);\nVP Product → adoption & roadmap (retention signals, feedback loops, prioritization);\nVP CS → net revenue retention (churn risk, expansion, onboarding).\n\n*Opening patterns:* name a consequence they're managing (\"When [function] scales faster\nthan process, [outcome] breaks first\"); a gap between expectation and reality; a hidden\ncost of the status quo; an organizational tension (\"Your team is executing. The outcome\nisn't reflecting it yet\").\n\n### Manager doctrine\nManagers **feel the friction directly** — they live broken processes, they don't read about\nthem. Squeezed from both sides (VP targets above, team asking for tools/clarity below). They\nare the primary *evaluator*, rarely the final decision-maker, so give them something worth\ninvestigating and easy to bring to their VP. They value the **HOW** over the vision and\ndistrust buzzwords.\n\n*Pain taxonomy:* Sales Manager → rep coaching, pipeline reviews, forecast calls (ramp, rep\nconsistency, deal visibility); RevOps Manager → data cleanup, integrations, reporting (stack\nsprawl, bad data, manual work); Marketing Manager → campaign execution, lead quality\n(MQL→SQL, attribution, production speed); CSM → renewals, escalations, health scoring;\nOps Manager → process reliability (recurring manual work, exception handling, adoption);\nSDR/BDR Manager → team activity, rep development (reply rates, meeting quality, ramp).\n\n*Opening patterns:* name a recurring team problem; a process gap (\"When [system] doesn't\nwork, [team] ends up [workaround]\"); a visibility gap (\"What your VP sees and what's actually\nhappening in [team] are rarely the same\"); a consistency gap.\n\n### IC doctrine\nICs **feel every broken thing in real time** and have no budget authority — but they're\npowerful champions if you give them something worth fighting for. The goal is not to close\nan IC; it's to make them say *\"I need to show this to [manager].\"* They're the most skeptical\nrecipients (most irrelevant outbound, fastest deletes), speak in specifics not abstractions,\nwant to look good to their manager, and respond to peer-to-peer honesty.\n\n*Pain taxonomy:* SDR/BDR → low reply rates, objection handling (wants meetings, recognition,\nfaster ramp); AE → stalled deals, forecast pressure (wants closed deals, clean pipeline);\nAccount Manager → renewal risk, upsell, coverage; CS Rep → escalations, health monitoring,\nonboarding; RevOps Analyst → manual data work, broken reports (wants to be seen as strategic);\nMarketing Specialist → content production, campaign performance, lead quality.\n\n*Opening patterns:* name the exact moment of frustration (\"When [specific activity], [specific\nbad outcome] — every time\"); the effort-to-result gap; the invisible problem; the recurring\nfail per cycle.\n\n---\n\n## Phase 4 — Write the 3-email sequence (shared)\n\n### Architecture\n\n```\nEmail 1 — Name the tension (hook & recognition; no product)\nEmail 2 — Root cause + proof (diagnose why it persists; PS with a real resource)\nEmail 3 — Tier-specific shift + breakup (see Phase 3 \"Email 3 move\")\n```\n\nEmail 1 names the pain at the tier's altitude. Email 2 diagnoses the *structural cause*\n(not the symptom) and adds a real, non-fabricated reference plus a PS resource. Email 3\napplies the tier's Email-3 move and ends with the breakup line.\n\n### Universal rules (non-negotiable, every email)\n\n- 50–100 words per body (excluding variables and PS). Hard channel cap: Email 1 (the first touch) never exceeds 120 words; keep every email to 4–7 sentences across no more than 3 short paragraphs\n- Subject line: exactly 2 words, all lowercase, sounds like an internal email; each email's subject differs\n- Never start with a question; at most one question per email — a second question splits the ask and drops replies\n- Never use \"I\" — always \"you\", \"your team\", \"your [function/task]\"; the first word of a message is never \"I\"\n- Never mention features or benefits — only their pain and outcomes\n- **Lead with their pain backed by a signal, not your product.** Open on a named trigger (funding, key hire, tool change) tied to the pain before any product enters. Email 1 never names your brand or product in the body — the product first appears in Email 2 at the earliest\n- No meeting/call/demo ask in Email 1 (the first touch) — the first email earns the reply; the meeting ask belongs to Email 2 and Email 3\n- Never fabricate metrics, case studies, or customer results\n- Never use \"saving time\" or \"saving money\"; no buzzwords (\"leverage\", \"optimize\", \"streamline\", \"innovative\", \"synergy\", \"cutting-edge\", \"revolutionize\", \"seamlessly\", \"excited to share\")\n- No emojis, ever; at most one exclamation mark across the whole email\n- No weak phrases: \"I believe\", \"just following up\", \"imagine if\", \"circling back\"; no AI-opener clichés (\"I hope this finds you well\", \"I came across your profile\")\n- When the copy cites the prospect's headcount, round it — never cite an exact count (exact numbers read as scraped data): under 500 → nearest 10; 500–2,000 → nearest 100; over 2,000 → nearest 1,000\n- One problem per email — no stacking\n- Short sentences — one line on mobile\n- Read-aloud test: must flow naturally in ~15 seconds\n- **The Human Writing Test (final gate on every email):** \"Would a real salesperson send this exact message from their personal account, unedited?\" If no, rewrite it before delivering\n\n### Email structure\n\n**Email 1 — Tension hook**\n```\n[Opening line — name the tension at the tier's altitude, 10–20 words, never a question]\n[2–3 sentences — develop it in their world, show you understand it, no product]\n[1 sentence — bridge to what's possible, without naming your product]\n[CTA — one clear, low-friction ask, weighted per tier]\n```\n\n**Email 2 — Root cause + proof**\n```\n[1 sentence — callback to Email 1's tension, new angle on it]\n[2–3 sentences — diagnose WHY it keeps happening (a diagnosis, not a complaint)]\n[1 sentence — what changes when the root cause is addressed]\n[CTA — slightly more direct than Email 1]\nP.S. [One sentence, a real company/situation — no fabricated outcome] + [a real resource tied to Email 1's topic]\n```\n\n**Email 3 — Tier shift + breakup**\n```\n[1 sentence — the tier's Email-3 move (stakeholder shift / consequence / champion angle)]\n[2–3 sentences — develop it briefly, not alarmist]\n[CTA — final, direct]\n[P.S. — resource tied to Email 2's theme]\nwon't message again, hope I didn't do something wrong!\n```\n\nThe breakup line is used verbatim as the last line of Email 3.\n\n---\n\n## Phase 5 — Personalization\n\nUse **Enginy single-brace placeholders** in subjects and bodies — e.g. `{firstName}`,\n`{companyName}`. Exact placeholder names are workspace-specific: discover them with\n`get_contact_field_metadata` (pass `search` to look one up) rather than guessing. Never\ninvent a placeholder that doesn't exist in the workspace, and never fake personalization\nin prose (\"as a VP of X you must have Y problem\").\n\nFor **personalization that scales across a list** (a researched one-liner per prospect —\ne.g. a line about their recent funding or hiring), that's an **AI variable**: mention\n`create_an_ai_variable` or route to the `ai-research-builder` skill, then reference the\nvariable as a placeholder in the copy.\n\nIf no variables are available, write the sequence to read perfectly with zero placeholders.\n\n---\n\n## Phase 6 — Output, then offer to push into Enginy\n\nPresent the sequence in this format:\n\n```\n### CAMPAIGN: [Persona] — [Angle Name]\nTarget: [Title] | [Team/reports-to if relevant] | [Industry / Company size]\nSeniority: [VP / Manager / IC]\nAngle: [one sentence]\nPersonalization variables used: [list or \"none\"]\n\nEMAIL 1  Subject: [word1 word2]\n[body]\n\nEMAIL 2  Subject: [word1 word2]\n[body]\nP.S. [resource]\n\nEMAIL 3  Subject: [word1 word2]\n[body]\nP.S. [resource]\nwon't message again, hope I didn't do something wrong!\n\n### SEQUENCE NOTES\n- Email 1 tension / Email 2 root cause / Email 3 shift\n- CTA progression across the three emails\n- What to A/B test first (subject, opening line, or CTA)\n```\n\nThen offer: **\"Want me to push this into Enginy as a campaign?\"** If yes:\n\n1. Build a `steps` array — one `email` step per email, in order:\n   `{ \"type\": \"email\", \"subject\": \"...\", \"content\": \"...\", \"delay\": { \"value\": N, \"unit\": \"days\" } }`.\n   Email 1 uses `delay` value `0` (or omit); Email 2 and Email 3 use the follow-up gaps\n   (default 3–5 days each — see `outbound-campaign-architect` for timing).\n2. Call `validate_campaign` with `{ name, steps }` first; fix any path-specific errors it reports.\n3. Call `create_campaign` with the same body. **Return the `appUrl` from the response to the user.**\n4. For full setup (identity, list, sending schedule, launch), route to the `launch-campaign` skill.\n\nDo not launch or start sending — this skill drafts the campaign only.\n\n---\n\n## Enginy MCP tools used\n\n- `get_a_single_contact` — pull a named prospect's record (title, seniority, industry) instead of asking\n- `get_a_single_company` — pull the prospect's account context\n- `get_contact_field_metadata` — discover valid single-brace personalization placeholders for the workspace\n- `create_an_ai_variable` — create a researched, per-prospect variable for scaled personalization\n- `validate_campaign` — validate the `{ name, steps }` payload before creating\n- `create_campaign` — create the draft campaign from the ordered `steps` model; returns `appUrl`\n\n---\n\n## Important Notes\n\n- **Voice:** if the user has a voice profile set up (see **voice-profile**), write every draft through it — greeting/sign-off habits, banned phrases, and language rules from the profile override generic defaults.\n\n- **Draft only.** This skill writes copy and, on request, creates a *draft* campaign. It never launches, starts sending, or adds contacts. Launch is `launch-campaign`.\n- **Credits:** `create_an_ai_variable` runs consume enrichment credits per contact when executed on a list; drafting copy and creating a campaign do not. Warn the user before running AI variables at scale.\n- **Placeholders are workspace-specific** — always confirm via `get_contact_field_metadata`; an invalid placeholder renders as literal text in the sent email.\n- **No fabrication, ever** — metrics, case studies, and outcomes must be real and provided. Unsupported claims get reframed as neutral observation or removed.\n- **No unsourced stats in copy.** Any platform statistic must be labelled \"based on Enginy platform data, as of 2026\" or left out.\n- Docs: https://docs.enginy.ai\n\n---\n\n## Examples\n\n**1. VP, real prospect in Enginy**\nUser: \"Write a sequence for Dana Ruiz, VP Sales — she's already in my workspace.\"\n→ Pull `get_a_single_contact` (Dana) + `get_a_single_company` (her account) → tier = VP →\nskip context questions already answered by the record → write 3 emails at strategic altitude\n(Email 3 shifts to board/CFO pressure) → offer to `validate_campaign` + `create_campaign`.\n\n**2. Manager, cold, no CRM record**\nUser: \"3 emails for RevOps Managers at Series B SaaS, we clean up their pipeline data.\"\n→ tier = Manager → ask only the missing offer/proof/variables in one message → write at\noperational altitude (Email 3 = consequence for their VP's view of the team) → note no\nplaceholders since no list data yet.\n\n**3. IC, ambiguous title**\nUser: \"Write a sequence for a Marketing Specialist.\"\n→ title maps to IC-tier (confirm if the user implies more seniority) → hyper-specific daily\nfriction, peer-to-peer tone, forward-to-manager CTAs, Email 3 makes them the internal hero.\n\n---\n\n## Troubleshooting\n\n| Problem | Fix |\n|---|---|\n| Seniority unclear from the persona | Ask the one Phase 1 question; map by accountability, not title string |\n| User names a prospect but no context given | Pull `get_a_single_contact` / `get_a_single_company` before asking |\n| Placeholder renders as literal text in the email | The name is wrong for this workspace — confirm via `get_contact_field_metadata` |\n| Copy needs a per-prospect research line | That's an AI variable — use `create_an_ai_variable` / `ai-research-builder`, then reference it |\n| `create_campaign` returns a validation error | Run `validate_campaign` first; errors give full paths like `steps[1].subject` — fix that node |\n| User wants to actually launch / add contacts | Out of scope here — route to `launch-campaign` |\n| User only wants one email | Standalone → `copywriting-first-touch`; single bump → `copywriting-follow-up` |\n| Sequence feels generic | Sharpen the tier's opening pattern and pain taxonomy; one problem per email, no stacking |\n"
}