← LushaCONTENT HISTORY

Update to Lusha

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

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Lusha and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Score and rank a list of companies or contacts the user already has (a CSV, a pasted list of domains or names, or a Lusha Workspace table) by fit to their ICP and by live buying signals, then split it into A, B and C tiers. Use when the user says \"prioritise this list\", \"score these accounts\", \"rank my target list\", \"which of these companies should I work first\", \"tier my accounts\", \"which of these leads are hot\", or brings a list and asks where to start. Not for finding new companies: use prospect, signal-prospect or lookalike-prospect for that.\n",
  "included_files": [],
  "name": "score-my-list",
  "skill_md_contents": "---\nname: score-my-list\ndescription: \"Score and rank a list of companies or contacts the user already has (a CSV, a pasted list of domains or names, or a Lusha Workspace table) by fit to their ICP and by live buying signals, then split it into A, B and C tiers. Use when the user says \\\"prioritise this list\\\", \\\"score these accounts\\\", \\\"rank my target list\\\", \\\"which of these companies should I work first\\\", \\\"tier my accounts\\\", \\\"which of these leads are hot\\\", or brings a list and asks where to start. Not for finding new companies: use prospect, signal-prospect or lookalike-prospect for that.\\n\"\n---\n\n# Score My List\n\nMost users start from a list they already own: a territory, an event export, a CRM view. This skill tells them which rows to work first, and why, using two Lusha scores:\n\n- **ICP fit score** (0–1): how closely the company matches the user's own Target Profile in Lusha. It needs a profile.\n- **Signal score** (0–1): how much buying-signal activity the company shows right now (hiring surges, funding, headcount growth and more). It needs no setup.\n\nTogether they make up the Score the user sees in the Lusha app.\n\n## Lusha call rules\n\n1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `score-my-list: `.\n2. Run the calls that use no quota first and branch on what they return. A missing profile gets a setup offer and a fallback, never an error. A tool missing from this session means the account's plan does not include it: take the fallback.\n3. Before every quota-using call, state how much of the quota already included in the user's existing Lusha account it will use, and wait for a yes. This workflow cannot change the user's account entitlement. On a 402, if the existing entitlement is insufficient, say so and offer to continue with previews or a smaller batch. Never suggest changing the user's account entitlement.\n4. Keep the chain short: every call counts toward the user's AI usage. Use the full batch size of each tool.\n\n## Step 1 — Read the list\n\nAccept any of:\n- **A CSV or pasted list.** Use one identifier per row, in this order of preference: Lusha id, domain, email (its domain is used), company name. For a contacts list, use email, LinkedIn URL, or first + last name + company.\n- **A Workspace table.** Find it with `table_list` (uses no quota). Get its row count with `table_status` (uses no quota), then read the rows with `table_get_entities`. Reading uses existing-account quota per block of rows (`tableRead` in `account_usage`), and quota for the full `page_size` is reserved up front, so set `page_size` to the row count (max 100 per page) and state the quota usage first.\n\nDecide whether the list is **companies** or **contacts**. A list of people with company columns can be scored either way; ask which the user cares about if it isn't clear.\n\nDrop exact duplicates and say how many rows will be scored.\n\n## Step 2 — Check for an ICP profile (uses no quota)\n\nCall `icp_profiles_get` with `status: \"active\"`.\n\n- **Active profiles exist.** Use up to 3 (the score tools take 1–3 `targetProfileIds`). If there are more than 3, list them and ask which to score against.\n- **No active profile, or the ICP tools are missing.** Score with signals only, and say: *\"You don't have an ICP profile in Lusha yet, so I'll rank by buying signals only. Want to set one up with set-up-my-icp after this, so I can score fit too?\"* Do not call the fit score tools: with no profile they fail and still give no score.\n\n## Step 3 — State the quota usage and score\n\nEstimate the quota for both scores from `account_usage` (`pricing`, the per-action quota rates; uses no quota), and give one total, e.g. *\"Scoring 180 companies uses about 360 of the quota already included in your existing Lusha account (180 fit + 180 signal). Go ahead?\"* If a score has no entry in `pricing`, say its rate isn't listed for this plan, and report the quota it actually used from the usage metadata afterwards. Offer signal-only as the option that uses less quota when a profile exists.\n\nThen score in full batches:\n- `icp_fit_score_companies` (or `_contacts`): up to **100** per call, with `targetProfileIds`.\n- `signal_score_companies` (or `_contacts`): up to **50** per call.\n\nSet each entry's `clientReferenceId` to its row number so results map back to the user's rows. Rows that come back with `error` from both tools (usually `NOT_FOUND`) are not tiered; list them at the end.\n\n**One score missing.** If one tool scored a row and the other returned an error (for example, fit `NO_SCORE` but signal 0.75), tier the row on the score it has, using the signals-only rules, and mark it \"fit unknown\". A hot account should not drop to C because its fit couldn't be computed.\n\n## Step 4 — Tier\n\nUse these rules, so every tier can be explained in one line:\n\n**With an ICP profile**\n- **A** — fit ≥ 0.6 **and** signal score ≥ 0.5. Right profile, moving now.\n- **B** — one of the two: good fit but quiet, or strong signals but weaker fit.\n- **C** — neither.\n\n**Signals only**\n- **A** — signal score ≥ 0.625.\n- **B** — signal score from 0.25 up to 0.625.\n- **C** — below 0.25, or no active signals.\n\nUse the score, not \"has any signal\": almost every company shows at least one active signal (a hiring surge is common), so any-signal would put nearly the whole list in A or B.\n\nThe signal threshold is higher with signals only (0.625) than alongside fit (0.5). That's deliberate:\n- **With a profile,** signal is one of two tests, and fit does the filtering.\n- **With signals only,** signal is the whole test, so A needs a higher bar. On real scores, 0.5 put most of a list in A.\n\nSo the same company can land in a different tier in the two modes. Say which mode was used (Step 5).\n\nWithin a tier, sort by fit, then signal score.\n\n## Step 5 — Present the result\n\n### Scored against\nName the profiles used, or say *\"buying signals only, no ICP profile\"*.\n\n### Tiers\n\n| Tier | # | Company | Domain | ICP fit | Top profile | Signal score | Active signals |\n|------|---|---------|--------|---------|-------------|--------------|----------------|\n\n- Show the A tier in full and the first 10 rows of B and C. Offer the full table as a CSV with every row, its tier, both scores and the signal types.\n- \"Active signals\" lists the `signalTypes` in plain words (e.g. \"hiring surge, headcount +6m\"), so the user sees why a row is hot.\n\n### Summary\n- Rows scored: X (not found: N)\n- A / B / C: a / b / c\n- Existing-account quota used: sum of the usage metadata\n\n## Step 6 — Next actions\n\n1. **Save the A tier to a Workspace table** — hand the A-tier ids to `save-or-export`. Lusha tables cannot hold a score or tier column, so name the table after the tier (`<list name> · A tier · <date>`) and keep the full ranking in the CSV. Saving companies uses the revealCompany quota rate per company; `save-or-export` states it.\n2. **Export the A tier to the CRM** — through `save-or-export`.\n3. **Find the decision makers at the A tier** — use `work-my-accounts` from its \"find people\" step, with these companies as the picked accounts.\n4. **No ICP profile?** Run `set-up-my-icp`, then score again for fit.\n"
}

SHA-256 of public snapshot: 9bc89d46030b8f1eaa00b7413f7631d75fb2d99e5f77c12381238f9e044d33b1