Update to Lusha
Snapshot Nov 9, 2026 · 00:08 UTC · version 3.1.0
Collection source: downloaded plugin package.
Instructions updated for signal-prospect
Skill instructions — Now says: ## Lusha call rules 1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `signal-prospect: `...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Oct 25, 2026 · 12:04 UTC
Use `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-acc...
Nov 9, 2026 · 00:08 UTC
## Lusha call rules 1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `signal-prospect: ` (or with the calling skill's name, when another skill delegated here, as `outre...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -7,6 +7,14 @@ Start from a buying signal — company or contact level — and end with a call-ready list of enriched decision makers. This is Lusha's core differentiated workflow: trigger → identify → phone reveal. +## Lusha call rules + +1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `signal-prospect: ` (or with the calling skill's name, when another skill delegated here, as `outreach-sequence` does). +2. State how much of the quota already included in the user's existing Lusha account every quota-using call uses, and wait for a yes on large batches. 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. +3. Zero results is not the end of the session: say what was searched and what coverage exists, then offer to widen (Step 4a). +4. Keep the chain short: every call counts toward the user's AI usage. +5. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`. + ## Step 1 — Identify the Signal Mode Determine which mode applies based on the user's request: @@ -62,6 +70,16 @@ **Contact signal mode** — `prospecting_contact_search` with `signals: { names: [...], startDate? }` (contact signals support `names` + `startDate` only). Request up to 50 results (`page_size`). +## Step 4a — When Discovery Comes Back Empty + +Never end the session on an empty result. Tell the user exactly what was searched, e.g. *"No companies with a Funding Round since 2026-09-01 among US fintech companies of 50–200 people."* Then offer the widenings that apply, most useful first: + +1. **Widen the date window** — if `startDate` was narrower than the 6-month default, offer to drop it. +2. **Related signal types** — offer one or two neighbouring types from the Step 2 directory (e.g. `headcountIncrease3m` alongside `surgeInHiring`, or the parent news type instead of a narrow sub-type). +3. **Loosen the company filters** — name the narrowest filter (size, location, industry) and offer to drop it. + +The same applies in Step 5. When `signals_companies_get` / `signals_contacts_get` returns `NO_SIGNALS_FOUND` for companies or contacts the user cares about, re-check those ids once without the narrow sub-type filter (the parent type only). The response's own `startDate` / `endDate` show the window that was searched. Then report the coverage that exists: *"No funding round since April; the latest financial news at Stayforlong is a revenue report from July."* If there is nothing even then, say this company has no recorded events of this type in the window. + ## Step 5 — Pull Signal Detail (Events, Dates, News Sub-Type) The discovery search returns the matched companies/contacts but not the underlying signal events or their dates. To surface the actual event, its date, and to keep only a specific news sub-type, run a signals lookup on the matched Lusha IDs: @@ -80,7 +98,15 @@ ## Step 7 — Enrich and Reveal Phones -Use `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-account quota the selected fields will use. This workflow cannot change the user's account entitlement. If the existing entitlement is insufficient, offer to continue with previews or a smaller batch. +Use `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-account quota the selected fields will use (the sum of `canReveal[].credits`) — use `account_usage` to check the remaining existing-account quota if needed. This workflow cannot change the user's account entitlement. If the existing entitlement is insufficient, offer to continue with previews or a smaller batch. + +**What a reveal returns.** +- **Third-party quota rates.** `canReveal[].credits` is Lusha's own quota rate. If the account has the data waterfall on, a Lusha miss can be filled by a third-party source at its own quota rate (`account_usage` lists them, e.g. a phone at 8 of the existing-account quota). Say so when stating the quota used. Offer `waterfallEnabled: false` for a Lusha-only reveal. +- **`COMPLIANCE_RESTRICTED`** on a row means that contact can't be shown, for compliance reasons, and no quota was used. Say so and offer the next person. +- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as "Do not call", never as a number to dial. +- **A different company.** If the enrich result shows a different company from the search, the person has changed jobs. Show the new company and say so. + +**Background reveals.** A `job` block in an enrich response means some reveals (usually from third-party sources) are still running. Show what has landed and how many are still running (`job.outstandingCount`). Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contacts with `contacts_enrich_job_results` (`contactLimit: 25`, following `contactPage.nextContactOffset` while `hasMore`). Never enrich the same ids again: that may use the existing-account quota twice. The job tools use no quota. Larger sets still go in calls of 50; each call may carry its own job. ## Step 8 — Present Results @@ -114,4 +140,6 @@ 1. **Narrow by geography or company size** — apply additional filters to the matched companies 2. **Change the target role** — re-run Step 6 with a different title or seniority 3. **Run a different signal** — try a related signal type (e.g. also check `headcountIncrease3m` alongside funding) -4. **Export** — format as CSV \ No newline at end of file +4. **Save to a Workspace table** — hand the contact ids to `save-or-export` (contacts tables use no quota) +5. **Export to CRM** — through `save-or-export`, which checks the CRM connection first and offers to connect one if there is none +6. **Export** — format as CSV
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: signal-prospect\ndescription: \"Find companies or contacts triggered by a buying signal, then surface verified phone numbers for the right decision makers. Use when the user says \\\"find companies that just raised funding\\\", \\\"who's surging in sales hiring right now\\\", \\\"show me companies with headcount growth\\\", \\\"find contacts who just got promoted\\\", \\\"who changed jobs recently in [industry]\\\", \\\"show me [title] at companies that just [signal event]\\\", or any request that starts with a real-world trigger rather than a static filter.\\n\"\n---\n\n# Signal-Prospect\n\nStart from a buying signal — company or contact level — and end with a call-ready list of enriched decision makers. This is Lusha's core differentiated workflow: trigger → identify → phone reveal.\n\n## Step 1 — Identify the Signal Mode\n\nDetermine which mode applies based on the user's request:\n\n**Company signal mode** — the trigger is something happening at a company (funding, hiring surge, headcount change, news event). Goal: find the right people at those companies and get their phones.\n\n**Contact signal mode** — the trigger is something happening to a person (got promoted, changed company). Goal: find those people and get their updated contact details.\n\nIf unclear, ask: *\"Are you looking for companies showing a specific signal, or individual contacts who recently changed roles or employers?\"*\n\n## Step 2 — Discover Available Signal Types and Sub-Filters\n\nThese tools are the authoritative source of valid signal identifiers — never assume a signal type exists without confirming it here, since invalid values are rejected with a 400.\n\n**Company signals:** Call `signals_company_filters` with no `filterType` to get the directory: `{ signalTypes, availableFilters: [{ filterType, requiresQuery }] }`. To enumerate the values for a sub-filter, call it again with `filterType` set to `newsEventTypes`, `hiringByDepartments`, or `hiringByLocations` (`hiringByLocations` requires a `query`).\n\n**Contact signals:** Call `signals_contact_filters` to get the supported contact signal types (e.g. `promotion`, `companyChange`, `allSignals`).\n\n## Step 3 — Map User Intent to a Signal Type\n\nMatch the user's phrasing to a signal identifier returned in Step 2. The table is a starting point — always validate the identifier against the live directory before using it:\n\n| User says | Signal type (`names`) | News sub-type (applied in Step 5) |\n|-----------|----------------------|-----------------------------------|\n| \"raised funding / Series A/B/C / IPO\" | `financialEventsNews` | `Funding Round`, `IPO`, `Strategic Investment` |\n| \"surging in hiring / lots of open roles\" | `surgeInHiring` | — |\n| \"growing fast / headcount up\" | `headcountIncrease3m` / `headcountIncrease6m` | — |\n| \"hiring sales reps\" | `surgeInHiringByDepartment` (+ `filterByDepartment`) | — |\n| \"new partnership / new customer\" | `commercialActivityNews` | `New Customer`, `Partnership`, `New Location` |\n| \"new product launch\" | `productActivityNews` | `Product Launch`, `Product Integration` |\n| \"executive just joined / new CRO\" | `peopleNews` | `Executive Hire`, `Executive Departure` |\n| \"contact just got promoted\" | contact signal `promotion` | — |\n| \"contact changed company / new job\" | contact signal `companyChange` | — |\n\nThe signal **type** (`names`) is what the discovery search in Step 4 accepts. The **news sub-type** (right column) is a different mechanism — it cannot be passed to the discovery search; it is applied in Step 5 via `signals_company_filters` values. If the user's intent doesn't map cleanly, present the closest available types and confirm.\n\n## Step 4 — Discover by Signal (Search)\n\nDiscovery narrows the population to companies/contacts that currently have the signal. The `signals` filter on the prospecting search tools is what does this — it accepts signal **type names** plus hiring sub-filters only.\n\n**Company signal mode** — `prospecting_company_search` with:\n\n```\nsignals: {\n names: [\"<signal type>\", ...], // OR-combined; from Step 2/3\n startDate: \"YYYY-MM-DD\", // optional; defaults to last 6 months\n filterByDepartment: [{ department }], // optional; for surgeInHiringByDepartment\n filterByLocation: [{ country, state }]// optional; for surgeInHiringByLocation\n}\n```\n\nCombine with ordinary company filters (industry, size, location — resolved via `prospecting_company_filters`) to scope the account population. News-event types like `Funding Round` **cannot** be narrowed here — pass the parent type (`financialEventsNews`) and narrow in Step 5.\n\n**Contact signal mode** — `prospecting_contact_search` with `signals: { names: [...], startDate? }` (contact signals support `names` + `startDate` only). Request up to 50 results (`page_size`).\n\n## Step 5 — Pull Signal Detail (Events, Dates, News Sub-Type)\n\nThe discovery search returns the matched companies/contacts but not the underlying signal events or their dates. To surface the actual event, its date, and to keep only a specific news sub-type, run a signals lookup on the matched Lusha IDs:\n\n**Company mode** — `signals_companies_get` with the matched company IDs. Pass `filters.include.newsEventTypes` (e.g. `[\"Funding Round\"]`), `hiringByDepartments`, or `hiringByLocations` to keep only the events you care about. Returns the signal events, date window, and usage metadata.\n\n**Contact mode** — `signals_contacts_get` with the matched contact IDs → promotion / company-change events with dates.\n\nThis step uses quota already included in the user's existing Lusha account, so run it only on the shortlist the user intends to act on and state the estimated quota usage first. If you have company/contact identifiers but no Lusha IDs (e.g. a user-supplied list of domains), use `signals_companies_search` / `signals_contacts_search` instead — they resolve the identifier and return signals in one call.\n\n## Step 6 — Find Decision Makers (Company Signal Mode Only)\n\nFor the matched companies, use `prospecting_contact_search` scoped to them via `companyDomains` or `companyNames`, plus the target role — `jobTitles` (free-form) or resolved `seniority` / `departments`. If no role was specified, ask: *\"What role are you looking to reach at these companies?\"*\n\nSkip this step in contact signal mode — the triggered contacts are already the targets.\n\n## Step 7 — Enrich and Reveal Phones\n\nUse `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-account quota the selected fields will use. This workflow cannot change the user's account entitlement. If the existing entitlement is insufficient, offer to continue with previews or a smaller batch.\n\n## Step 8 — Present Results\n\n### Signal Used\nState exactly which signal was applied and what it means (e.g., \"Funding Round events since 2026-05-01\").\n\n### Results\n\n**Company signal mode:**\n\n| # | Company | Signal | Signal Date | Contact Name | Title | Direct Phone | Mobile | Email |\n|---|---------|--------|-------------|-------------|-------|-------------|--------|-------|\n\n**Contact signal mode:**\n\n| # | Name | Signal | Previous Role | New Role / Company | Direct Phone | Mobile | Email |\n|---|------|--------|--------------|-------------------|-------------|--------|-------|\n\n- Lead with phone columns — never bury them at the end\n- Mark missing phones with `—`\n- Surface the signal date (from Step 5) so the user knows how fresh the trigger is\n\n### Summary\n- Companies / contacts matched: X\n- Decision makers found: Y\n- Verified phones revealed: Z\n- Existing-account quota used: N\n\n## Step 9 — Offer Next Actions\n\n1. **Narrow by geography or company size** — apply additional filters to the matched companies\n2. **Change the target role** — re-run Step 6 with a different title or seniority\n3. **Run a different signal** — try a related signal type (e.g. also check `headcountIncrease3m` alongside funding)\n4. **Export** — format as CSV""---\nname: signal-prospect\ndescription: \"Find companies or contacts triggered by a buying signal, then surface verified phone numbers for the right decision makers. Use when the user says \\\"find companies that just raised funding\\\", \\\"who's surging in sales hiring right now\\\", \\\"show me companies with headcount growth\\\", \\\"find contacts who just got promoted\\\", \\\"who changed jobs recently in [industry]\\\", \\\"show me [title] at companies that just [signal event]\\\", or any request that starts with a real-world trigger rather than a static filter.\\n\"\n---\n\n# Signal-Prospect\n\nStart from a buying signal — company or contact level — and end with a call-ready list of enriched decision makers. This is Lusha's core differentiated workflow: trigger → identify → phone reveal.\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 `signal-prospect: ` (or with the calling skill's name, when another skill delegated here, as `outreach-sequence` does).\n2. State how much of the quota already included in the user's existing Lusha account every quota-using call uses, and wait for a yes on large batches. 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.\n3. Zero results is not the end of the session: say what was searched and what coverage exists, then offer to widen (Step 4a).\n4. Keep the chain short: every call counts toward the user's AI usage.\n5. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.\n\n## Step 1 — Identify the Signal Mode\n\nDetermine which mode applies based on the user's request:\n\n**Company signal mode** — the trigger is something happening at a company (funding, hiring surge, headcount change, news event). Goal: find the right people at those companies and get their phones.\n\n**Contact signal mode** — the trigger is something happening to a person (got promoted, changed company). Goal: find those people and get their updated contact details.\n\nIf unclear, ask: *\"Are you looking for companies showing a specific signal, or individual contacts who recently changed roles or employers?\"*\n\n## Step 2 — Discover Available Signal Types and Sub-Filters\n\nThese tools are the authoritative source of valid signal identifiers — never assume a signal type exists without confirming it here, since invalid values are rejected with a 400.\n\n**Company signals:** Call `signals_company_filters` with no `filterType` to get the directory: `{ signalTypes, availableFilters: [{ filterType, requiresQuery }] }`. To enumerate the values for a sub-filter, call it again with `filterType` set to `newsEventTypes`, `hiringByDepartments`, or `hiringByLocations` (`hiringByLocations` requires a `query`).\n\n**Contact signals:** Call `signals_contact_filters` to get the supported contact signal types (e.g. `promotion`, `companyChange`, `allSignals`).\n\n## Step 3 — Map User Intent to a Signal Type\n\nMatch the user's phrasing to a signal identifier returned in Step 2. The table is a starting point — always validate the identifier against the live directory before using it:\n\n| User says | Signal type (`names`) | News sub-type (applied in Step 5) |\n|-----------|----------------------|-----------------------------------|\n| \"raised funding / Series A/B/C / IPO\" | `financialEventsNews` | `Funding Round`, `IPO`, `Strategic Investment` |\n| \"surging in hiring / lots of open roles\" | `surgeInHiring` | — |\n| \"growing fast / headcount up\" | `headcountIncrease3m` / `headcountIncrease6m` | — |\n| \"hiring sales reps\" | `surgeInHiringByDepartment` (+ `filterByDepartment`) | — |\n| \"new partnership / new customer\" | `commercialActivityNews` | `New Customer`, `Partnership`, `New Location` |\n| \"new product launch\" | `productActivityNews` | `Product Launch`, `Product Integration` |\n| \"executive just joined / new CRO\" | `peopleNews` | `Executive Hire`, `Executive Departure` |\n| \"contact just got promoted\" | contact signal `promotion` | — |\n| \"contact changed company / new job\" | contact signal `companyChange` | — |\n\nThe signal **type** (`names`) is what the discovery search in Step 4 accepts. The **news sub-type** (right column) is a different mechanism — it cannot be passed to the discovery search; it is applied in Step 5 via `signals_company_filters` values. If the user's intent doesn't map cleanly, present the closest available types and confirm.\n\n## Step 4 — Discover by Signal (Search)\n\nDiscovery narrows the population to companies/contacts that currently have the signal. The `signals` filter on the prospecting search tools is what does this — it accepts signal **type names** plus hiring sub-filters only.\n\n**Company signal mode** — `prospecting_company_search` with:\n\n```\nsignals: {\n names: [\"<signal type>\", ...], // OR-combined; from Step 2/3\n startDate: \"YYYY-MM-DD\", // optional; defaults to last 6 months\n filterByDepartment: [{ department }], // optional; for surgeInHiringByDepartment\n filterByLocation: [{ country, state }]// optional; for surgeInHiringByLocation\n}\n```\n\nCombine with ordinary company filters (industry, size, location — resolved via `prospecting_company_filters`) to scope the account population. News-event types like `Funding Round` **cannot** be narrowed here — pass the parent type (`financialEventsNews`) and narrow in Step 5.\n\n**Contact signal mode** — `prospecting_contact_search` with `signals: { names: [...], startDate? }` (contact signals support `names` + `startDate` only). Request up to 50 results (`page_size`).\n\n## Step 4a — When Discovery Comes Back Empty\n\nNever end the session on an empty result. Tell the user exactly what was searched, e.g. *\"No companies with a Funding Round since 2026-09-01 among US fintech companies of 50–200 people.\"* Then offer the widenings that apply, most useful first:\n\n1. **Widen the date window** — if `startDate` was narrower than the 6-month default, offer to drop it.\n2. **Related signal types** — offer one or two neighbouring types from the Step 2 directory (e.g. `headcountIncrease3m` alongside `surgeInHiring`, or the parent news type instead of a narrow sub-type).\n3. **Loosen the company filters** — name the narrowest filter (size, location, industry) and offer to drop it.\n\nThe same applies in Step 5. When `signals_companies_get` / `signals_contacts_get` returns `NO_SIGNALS_FOUND` for companies or contacts the user cares about, re-check those ids once without the narrow sub-type filter (the parent type only). The response's own `startDate` / `endDate` show the window that was searched. Then report the coverage that exists: *\"No funding round since April; the latest financial news at Stayforlong is a revenue report from July.\"* If there is nothing even then, say this company has no recorded events of this type in the window.\n\n## Step 5 — Pull Signal Detail (Events, Dates, News Sub-Type)\n\nThe discovery search returns the matched companies/contacts but not the underlying signal events or their dates. To surface the actual event, its date, and to keep only a specific news sub-type, run a signals lookup on the matched Lusha IDs:\n\n**Company mode** — `signals_companies_get` with the matched company IDs. Pass `filters.include.newsEventTypes` (e.g. `[\"Funding Round\"]`), `hiringByDepartments`, or `hiringByLocations` to keep only the events you care about. Returns the signal events, date window, and usage metadata.\n\n**Contact mode** — `signals_contacts_get` with the matched contact IDs → promotion / company-change events with dates.\n\nThis step uses quota already included in the user's existing Lusha account, so run it only on the shortlist the user intends to act on and state the estimated quota usage first. If you have company/contact identifiers but no Lusha IDs (e.g. a user-supplied list of domains), use `signals_companies_search` / `signals_contacts_search` instead — they resolve the identifier and return signals in one call.\n\n## Step 6 — Find Decision Makers (Company Signal Mode Only)\n\nFor the matched companies, use `prospecting_contact_search` scoped to them via `companyDomains` or `companyNames`, plus the target role — `jobTitles` (free-form) or resolved `seniority` / `departments`. If no role was specified, ask: *\"What role are you looking to reach at these companies?\"*\n\nSkip this step in contact signal mode — the triggered contacts are already the targets.\n\n## Step 7 — Enrich and Reveal Phones\n\nUse `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-account quota the selected fields will use (the sum of `canReveal[].credits`) — use `account_usage` to check the remaining existing-account quota if needed. This workflow cannot change the user's account entitlement. If the existing entitlement is insufficient, offer to continue with previews or a smaller batch.\n\n**What a reveal returns.**\n- **Third-party quota rates.** `canReveal[].credits` is Lusha's own quota rate. If the account has the data waterfall on, a Lusha miss can be filled by a third-party source at its own quota rate (`account_usage` lists them, e.g. a phone at 8 of the existing-account quota). Say so when stating the quota used. Offer `waterfallEnabled: false` for a Lusha-only reveal.\n- **`COMPLIANCE_RESTRICTED`** on a row means that contact can't be shown, for compliance reasons, and no quota was used. Say so and offer the next person.\n- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as \"Do not call\", never as a number to dial.\n- **A different company.** If the enrich result shows a different company from the search, the person has changed jobs. Show the new company and say so.\n\n**Background reveals.** A `job` block in an enrich response means some reveals (usually from third-party sources) are still running. Show what has landed and how many are still running (`job.outstandingCount`). Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contacts with `contacts_enrich_job_results` (`contactLimit: 25`, following `contactPage.nextContactOffset` while `hasMore`). Never enrich the same ids again: that may use the existing-account quota twice. The job tools use no quota. Larger sets still go in calls of 50; each call may carry its own job.\n\n## Step 8 — Present Results\n\n### Signal Used\nState exactly which signal was applied and what it means (e.g., \"Funding Round events since 2026-05-01\").\n\n### Results\n\n**Company signal mode:**\n\n| # | Company | Signal | Signal Date | Contact Name | Title | Direct Phone | Mobile | Email |\n|---|---------|--------|-------------|-------------|-------|-------------|--------|-------|\n\n**Contact signal mode:**\n\n| # | Name | Signal | Previous Role | New Role / Company | Direct Phone | Mobile | Email |\n|---|------|--------|--------------|-------------------|-------------|--------|-------|\n\n- Lead with phone columns — never bury them at the end\n- Mark missing phones with `—`\n- Surface the signal date (from Step 5) so the user knows how fresh the trigger is\n\n### Summary\n- Companies / contacts matched: X\n- Decision makers found: Y\n- Verified phones revealed: Z\n- Existing-account quota used: N\n\n## Step 9 — Offer Next Actions\n\n1. **Narrow by geography or company size** — apply additional filters to the matched companies\n2. **Change the target role** — re-run Step 6 with a different title or seniority\n3. **Run a different signal** — try a related signal type (e.g. also check `headcountIncrease3m` alongside funding)\n4. **Save to a Workspace table** — hand the contact ids to `save-or-export` (contacts tables use no quota)\n5. **Export to CRM** — through `save-or-export`, which checks the CRM connection first and offers to connect one if there is none\n6. **Export** — format as CSV\n"Full snapshot data
{
"description": "Find companies or contacts triggered by a buying signal, then surface verified phone numbers for the right decision makers. Use when the user says \"find companies that just raised funding\", \"who's surging in sales hiring right now\", \"show me companies with headcount growth\", \"find contacts who just got promoted\", \"who changed jobs recently in [industry]\", \"show me [title] at companies that just [signal event]\", or any request that starts with a real-world trigger rather than a static filter.\n",
"included_files": [
{
"relative_path": "references/signal-guide.md",
"size_in_bytes": 4592
}
],
"name": "signal-prospect",
"skill_md_contents": "---\nname: signal-prospect\ndescription: \"Find companies or contacts triggered by a buying signal, then surface verified phone numbers for the right decision makers. Use when the user says \\\"find companies that just raised funding\\\", \\\"who's surging in sales hiring right now\\\", \\\"show me companies with headcount growth\\\", \\\"find contacts who just got promoted\\\", \\\"who changed jobs recently in [industry]\\\", \\\"show me [title] at companies that just [signal event]\\\", or any request that starts with a real-world trigger rather than a static filter.\\n\"\n---\n\n# Signal-Prospect\n\nStart from a buying signal — company or contact level — and end with a call-ready list of enriched decision makers. This is Lusha's core differentiated workflow: trigger → identify → phone reveal.\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 `signal-prospect: ` (or with the calling skill's name, when another skill delegated here, as `outreach-sequence` does).\n2. State how much of the quota already included in the user's existing Lusha account every quota-using call uses, and wait for a yes on large batches. 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.\n3. Zero results is not the end of the session: say what was searched and what coverage exists, then offer to widen (Step 4a).\n4. Keep the chain short: every call counts toward the user's AI usage.\n5. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.\n\n## Step 1 — Identify the Signal Mode\n\nDetermine which mode applies based on the user's request:\n\n**Company signal mode** — the trigger is something happening at a company (funding, hiring surge, headcount change, news event). Goal: find the right people at those companies and get their phones.\n\n**Contact signal mode** — the trigger is something happening to a person (got promoted, changed company). Goal: find those people and get their updated contact details.\n\nIf unclear, ask: *\"Are you looking for companies showing a specific signal, or individual contacts who recently changed roles or employers?\"*\n\n## Step 2 — Discover Available Signal Types and Sub-Filters\n\nThese tools are the authoritative source of valid signal identifiers — never assume a signal type exists without confirming it here, since invalid values are rejected with a 400.\n\n**Company signals:** Call `signals_company_filters` with no `filterType` to get the directory: `{ signalTypes, availableFilters: [{ filterType, requiresQuery }] }`. To enumerate the values for a sub-filter, call it again with `filterType` set to `newsEventTypes`, `hiringByDepartments`, or `hiringByLocations` (`hiringByLocations` requires a `query`).\n\n**Contact signals:** Call `signals_contact_filters` to get the supported contact signal types (e.g. `promotion`, `companyChange`, `allSignals`).\n\n## Step 3 — Map User Intent to a Signal Type\n\nMatch the user's phrasing to a signal identifier returned in Step 2. The table is a starting point — always validate the identifier against the live directory before using it:\n\n| User says | Signal type (`names`) | News sub-type (applied in Step 5) |\n|-----------|----------------------|-----------------------------------|\n| \"raised funding / Series A/B/C / IPO\" | `financialEventsNews` | `Funding Round`, `IPO`, `Strategic Investment` |\n| \"surging in hiring / lots of open roles\" | `surgeInHiring` | — |\n| \"growing fast / headcount up\" | `headcountIncrease3m` / `headcountIncrease6m` | — |\n| \"hiring sales reps\" | `surgeInHiringByDepartment` (+ `filterByDepartment`) | — |\n| \"new partnership / new customer\" | `commercialActivityNews` | `New Customer`, `Partnership`, `New Location` |\n| \"new product launch\" | `productActivityNews` | `Product Launch`, `Product Integration` |\n| \"executive just joined / new CRO\" | `peopleNews` | `Executive Hire`, `Executive Departure` |\n| \"contact just got promoted\" | contact signal `promotion` | — |\n| \"contact changed company / new job\" | contact signal `companyChange` | — |\n\nThe signal **type** (`names`) is what the discovery search in Step 4 accepts. The **news sub-type** (right column) is a different mechanism — it cannot be passed to the discovery search; it is applied in Step 5 via `signals_company_filters` values. If the user's intent doesn't map cleanly, present the closest available types and confirm.\n\n## Step 4 — Discover by Signal (Search)\n\nDiscovery narrows the population to companies/contacts that currently have the signal. The `signals` filter on the prospecting search tools is what does this — it accepts signal **type names** plus hiring sub-filters only.\n\n**Company signal mode** — `prospecting_company_search` with:\n\n```\nsignals: {\n names: [\"<signal type>\", ...], // OR-combined; from Step 2/3\n startDate: \"YYYY-MM-DD\", // optional; defaults to last 6 months\n filterByDepartment: [{ department }], // optional; for surgeInHiringByDepartment\n filterByLocation: [{ country, state }]// optional; for surgeInHiringByLocation\n}\n```\n\nCombine with ordinary company filters (industry, size, location — resolved via `prospecting_company_filters`) to scope the account population. News-event types like `Funding Round` **cannot** be narrowed here — pass the parent type (`financialEventsNews`) and narrow in Step 5.\n\n**Contact signal mode** — `prospecting_contact_search` with `signals: { names: [...], startDate? }` (contact signals support `names` + `startDate` only). Request up to 50 results (`page_size`).\n\n## Step 4a — When Discovery Comes Back Empty\n\nNever end the session on an empty result. Tell the user exactly what was searched, e.g. *\"No companies with a Funding Round since 2026-09-01 among US fintech companies of 50–200 people.\"* Then offer the widenings that apply, most useful first:\n\n1. **Widen the date window** — if `startDate` was narrower than the 6-month default, offer to drop it.\n2. **Related signal types** — offer one or two neighbouring types from the Step 2 directory (e.g. `headcountIncrease3m` alongside `surgeInHiring`, or the parent news type instead of a narrow sub-type).\n3. **Loosen the company filters** — name the narrowest filter (size, location, industry) and offer to drop it.\n\nThe same applies in Step 5. When `signals_companies_get` / `signals_contacts_get` returns `NO_SIGNALS_FOUND` for companies or contacts the user cares about, re-check those ids once without the narrow sub-type filter (the parent type only). The response's own `startDate` / `endDate` show the window that was searched. Then report the coverage that exists: *\"No funding round since April; the latest financial news at Stayforlong is a revenue report from July.\"* If there is nothing even then, say this company has no recorded events of this type in the window.\n\n## Step 5 — Pull Signal Detail (Events, Dates, News Sub-Type)\n\nThe discovery search returns the matched companies/contacts but not the underlying signal events or their dates. To surface the actual event, its date, and to keep only a specific news sub-type, run a signals lookup on the matched Lusha IDs:\n\n**Company mode** — `signals_companies_get` with the matched company IDs. Pass `filters.include.newsEventTypes` (e.g. `[\"Funding Round\"]`), `hiringByDepartments`, or `hiringByLocations` to keep only the events you care about. Returns the signal events, date window, and usage metadata.\n\n**Contact mode** — `signals_contacts_get` with the matched contact IDs → promotion / company-change events with dates.\n\nThis step uses quota already included in the user's existing Lusha account, so run it only on the shortlist the user intends to act on and state the estimated quota usage first. If you have company/contact identifiers but no Lusha IDs (e.g. a user-supplied list of domains), use `signals_companies_search` / `signals_contacts_search` instead — they resolve the identifier and return signals in one call.\n\n## Step 6 — Find Decision Makers (Company Signal Mode Only)\n\nFor the matched companies, use `prospecting_contact_search` scoped to them via `companyDomains` or `companyNames`, plus the target role — `jobTitles` (free-form) or resolved `seniority` / `departments`. If no role was specified, ask: *\"What role are you looking to reach at these companies?\"*\n\nSkip this step in contact signal mode — the triggered contacts are already the targets.\n\n## Step 7 — Enrich and Reveal Phones\n\nUse `prospecting_contact_enrich` with the contact `id`s to reveal direct and mobile numbers. Set `reveal` from each result's `canReveal[].field`; up to **50** contacts per call. Before enriching a large batch, state how much existing-account quota the selected fields will use (the sum of `canReveal[].credits`) — use `account_usage` to check the remaining existing-account quota if needed. This workflow cannot change the user's account entitlement. If the existing entitlement is insufficient, offer to continue with previews or a smaller batch.\n\n**What a reveal returns.**\n- **Third-party quota rates.** `canReveal[].credits` is Lusha's own quota rate. If the account has the data waterfall on, a Lusha miss can be filled by a third-party source at its own quota rate (`account_usage` lists them, e.g. a phone at 8 of the existing-account quota). Say so when stating the quota used. Offer `waterfallEnabled: false` for a Lusha-only reveal.\n- **`COMPLIANCE_RESTRICTED`** on a row means that contact can't be shown, for compliance reasons, and no quota was used. Say so and offer the next person.\n- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as \"Do not call\", never as a number to dial.\n- **A different company.** If the enrich result shows a different company from the search, the person has changed jobs. Show the new company and say so.\n\n**Background reveals.** A `job` block in an enrich response means some reveals (usually from third-party sources) are still running. Show what has landed and how many are still running (`job.outstandingCount`). Then check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true, and read the final contacts with `contacts_enrich_job_results` (`contactLimit: 25`, following `contactPage.nextContactOffset` while `hasMore`). Never enrich the same ids again: that may use the existing-account quota twice. The job tools use no quota. Larger sets still go in calls of 50; each call may carry its own job.\n\n## Step 8 — Present Results\n\n### Signal Used\nState exactly which signal was applied and what it means (e.g., \"Funding Round events since 2026-05-01\").\n\n### Results\n\n**Company signal mode:**\n\n| # | Company | Signal | Signal Date | Contact Name | Title | Direct Phone | Mobile | Email |\n|---|---------|--------|-------------|-------------|-------|-------------|--------|-------|\n\n**Contact signal mode:**\n\n| # | Name | Signal | Previous Role | New Role / Company | Direct Phone | Mobile | Email |\n|---|------|--------|--------------|-------------------|-------------|--------|-------|\n\n- Lead with phone columns — never bury them at the end\n- Mark missing phones with `—`\n- Surface the signal date (from Step 5) so the user knows how fresh the trigger is\n\n### Summary\n- Companies / contacts matched: X\n- Decision makers found: Y\n- Verified phones revealed: Z\n- Existing-account quota used: N\n\n## Step 9 — Offer Next Actions\n\n1. **Narrow by geography or company size** — apply additional filters to the matched companies\n2. **Change the target role** — re-run Step 6 with a different title or seniority\n3. **Run a different signal** — try a related signal type (e.g. also check `headcountIncrease3m` alongside funding)\n4. **Save to a Workspace table** — hand the contact ids to `save-or-export` (contacts tables use no quota)\n5. **Export to CRM** — through `save-or-export`, which checks the CRM connection first and offers to connect one if there is none\n6. **Export** — format as CSV\n"
}SHA-256 of public snapshot: 9cfd8395f12d9add1850af7f88c9387d5dddf325e621922e48794a9da28ca88e