Update to Lusha

{
  "name": "lookalike-prospect",
  "description": "Find companies or contacts similar to a set of references, then enrich results with verified phone numbers. Use when the user says \"find companies like my best customers\", \"find more contacts like these\", \"expand from these accounts\", \"who else looks like [company]\", \"find similar companies to [list]\", or any request to discover lookalike targets from a reference set. Requires at least 5 reference companies or contacts for quality results.",
  "included_files": [],
  "skill_md_contents": "---\nname: lookalike-prospect\ndescription: >\n  Find companies or contacts similar to a set of references, then enrich results with\n  verified phone numbers. Use when the user says \"find companies like my best customers\",\n  \"find more contacts like these\", \"expand from these accounts\", \"who else looks like [company]\",\n  \"find similar companies to [list]\", or any request to discover lookalike targets\n  from a reference set. Requires at least 5 reference companies or contacts for quality results.\n---\n\n# Lookalike Prospect\n\nExpand an ICP from a reference set of known-good companies or contacts. Requires a minimum of 5 references — the lookalike model degrades significantly below this threshold.\n\n## Step 1 — Validate Input Count\n\nCount the number of reference companies or contacts provided.\n\n**If fewer than 5 are provided**, stop and explain before doing anything else:\n\n> \"Lusha's lookalike model needs at least 5 reference [companies/contacts] to return quality results — fewer than that produces unreliable matches. You've provided [N]. Can you add [5−N] more?\"\n\nDo not proceed until the user has provided at least 5 references.\n\n**If 5 or more are provided**, confirm the reference set with the user:\n\n> \"Running lookalike search using these [N] [companies/contacts] as the reference set: [list]. Shall I proceed?\"\n\n## Step 2 — Determine Mode\n\nBased on the user's input, determine whether this is a **company lookalike** or **contact lookalike** search:\n\n- References are companies (domains, LinkedIn company URLs, or names) → **company mode**\n- References are people (emails, LinkedIn profile URLs, or name + company) → **contact mode**\n- Mixed input → ask the user to clarify\n\nA bare job title is not a valid seed — a lookalike needs concrete reference companies or people. If the user only has a persona/title in mind, route them to `prospect` (ICP search) or `signal-prospect` instead.\n\n## Step 3 — Assemble the Seed Set\n\nThe lookalike tools accept raw identifiers directly as seeds — no enrichment or Lusha-ID resolution is needed in the common case. Pass the references straight through. The seed count (5–100) is the **total** identifiers across the seed arrays.\n\n**Company mode** — `lookalike_companies.seeds` accepts:\n- `domains` (e.g. `lusha.com`)\n- `linkedinUrls` (company page URLs)\n\nIf the user gave company **names** rather than domains, resolve each name to a domain first with `companies_search` (`enrich: false` — you only need the domain, not reveal data), since the seed schema does not accept bare names. If a name can't be resolved, flag it and proceed only if ≥5 seeds remain.\n\n**Contact mode** — `lookalike_contacts.seeds` accepts any mix of:\n- `emails`\n- `linkedinUrls` (profile URLs)\n- `contacts` — `{ firstName, lastName, companyDomain | companyName }`\n- `contactIds` — Lusha contact IDs, if you already have them\n\nPass whatever form the user provided directly. No lookup step is needed.\n\n## Step 4 — Run Lookalike Search\n\n**Company mode:** Use `lookalike_companies` with the seed set. `limit` up to 100 (default 25).\n\n**Contact mode:** Use `lookalike_contacts` with the seed set. `limit` up to 50 (default 25).\n\nPass any known customers/won accounts in `exclude` (same identifier shape as `seeds`) to keep them out of the results. Results paginate via `dedupeSessionId`: omit it on the first call, then pass the returned token back on follow-up calls for the same seeds to fetch more non-duplicate matches (sessions expire after 30 days).\n\n## Step 5 — Find Decision Makers (Company Mode Only)\n\nFor the lookalike companies, use `prospecting_contact_search` scoped to them via `companyDomains` or `companyNames`, plus the target role. If the user hasn't specified one, ask: *\"What title or seniority are you targeting at these companies?\"*\n\nPass a specific title directly as `jobTitles` (free-form); for broader targeting, resolve `seniority` / `departments` via `prospecting_contact_filters` first.\n\n## Step 6 — Enrich and Reveal Phones\n\nSearch results are previews carrying a `canReveal[]` list per contact. Use `prospecting_contact_enrich` with the contact `id`s and `reveal` set from `canReveal[].field` to reveal direct and mobile numbers — up to **50** contacts per call. Before enriching a large batch, state how much quota already included in the user's existing Lusha account the selected fields will use. This workflow cannot change the user's account entitlement.\n\n## Step 7 — Present Results\n\n### Reference Set Used\nList the [N] references that were used. Flag any that could not be resolved.\n\n### Lookalike Results\n\n**Company mode:**\n\n| # | Company | Industry | Size | Revenue | Location | Contact Name | Title | Direct Phone | Mobile | Email |\n|---|---------|----------|------|---------|----------|-------------|-------|-------------|--------|-------|\n\n**Contact mode:**\n\n| # | Name | Title | Company | Industry | Direct Phone | Mobile | Email |\n|---|------|-------|---------|----------|-------------|--------|-------|\n\n- Phone columns always appear before email — never reversed\n- Mark missing phones with `—`\n\n### Summary\n- Lookalike [companies/contacts] found: X\n- Decision makers enriched: Y\n- Verified phones revealed: Z\n\n## Step 8 — Offer Next Actions\n\n1. **Narrow results** — apply additional filters (industry, geography, company size) to the lookalike list\n2. **Cross with signals** — run `signal-prospect` on this lookalike list to surface which ones are showing buying signals right now\n3. **Expand the reference set** — add more references to improve match quality\n4. **Export** — format as CSV\n"
}