Update to Vibe Prospecting Sourcing

{
  "description": "Find companies that resemble a seed company by rebuilding its industry, size, region and tech-stack profile and searching for others that share it. Use for 'find companies like Stripe', 'lookalike accounts for Acme', 'similar companies to our best customer', 'expand my territory', 'extend this account list'. Not for similar people (use talent-sourcing) or for comparing named rivals (use competitor-research). Results are an approximation, not a similarity score.",
  "included_files": [],
  "name": "lookalike-accounts",
  "skill_md_contents": "---\nname: lookalike-accounts\ndescription: \"Find companies that resemble a seed company by rebuilding its industry, size, region and tech-stack profile and searching for others that share it. Use for 'find companies like Stripe', 'lookalike accounts for Acme', 'similar companies to our best customer', 'expand my territory', 'extend this account list'. Not for similar people (use talent-sourcing) or for comparing named rivals (use competitor-research). Results are an approximation, not a similarity score.\"\n---\n\n# Lookalike Accounts\n\nRebuild the profile of one seed company, then search for companies that share it.\n\n## Connector rules\n\nUse only the Vibe Prospecting tools in your tool list. Each tool's live description and input schema are authoritative; if this skill disagrees with a tool, follow the tool.\n\n- **`tool_reasoning`** is required on every call: one short sentence (≤200 characters) that paraphrases what the user wants. No earlier conversation, contact details, or other personal data.\n- **Chaining:** copy `session_id` and `table_name` from the previous tool response; never invent either. After an enrich or events step, use the new `table_name`.\n- **`autocomplete` first**, one concept per call, for `linkedin_category`, `naics_category`, `company_tech_stack_tech`, `job_title`, `interests`, `skills`, `business_intent_topics`, and US `city_region`. Use the returned values as-is.\n- **What you can see:** `match-business` and `match-prospects` return complete results; fetch, enrich, and events tools return only a masked preview, so never quote values from it; `fetch-entities-statistics` returns aggregates; `show-sample` reveals up to 5 full rows.\n- **Finish with `show-sample`**, once per final `table_name`, then reply. Match-only and statistics-only work does not need it. The widget displays the sample rows, so do not repeat them as a table; use them for your analysis. If `display_status` is `masked`, say the full rows could not be revealed.\n- **Export** only after the user explicitly confirms, because it consumes credits. Show the returned download `url`. Never mention table names or session IDs to the user.\n- **Uploads:** you cannot upload files to Vibe Prospecting. Pasted lists and text from attached files are fine to use. If the user asks how to upload a list, point them to the Vibe Prospecting Hub: https://app.vibeprospecting.ai/lists\n\n## Input\n\n- **Seed company** (required): a name or domain. If the user gives a person, or asks for similar people, use talent-sourcing instead; this skill returns companies.\n- **Count:** default 25, up to 100.\n- **Overrides (optional):** country or region focus, size or revenue bucket, public-only, and extra tech-stack requirements.\n\n## Workflow\n\n1. **Match the seed** with `match-business`, using name and domain. If several candidates return, pick the one whose domain matches and say which you chose. If none resolves, ask for a domain.\n2. **Check the seed.** A big brand that resolves to 1-50 employees under \"Corporate Managing Offices\" is a shell entity. Retry with the other domain, since a wrong seed produces unrelated results.\n3. **Read the seed's profile** with `enrich-business-firmographics` and `enrich-business-technographics`, then `show-sample` on the enriched table to see the values. Take: industry (LinkedIn or NAICS, whichever is populated), headcount and revenue bucket, country (or the region the user asked for), and the top 3-5 technologies, favoring category-defining tools (CRM, marketing automation, data warehouse, cloud) over ubiquitous ones. Skip anything that comes back empty and do not guess. (The `show-sample` call here reads the enrichment values, it is not the final presentation.)\n4. **Resolve values** with `autocomplete` for the industry and each technology. For flagship vendors, try the product-qualified name first (\"Snowflake Data Cloud\", \"Stripe Payments\"), because the bare name often returns noise. Drop anything that does not resolve cleanly, and tell the user.\n5. **Apply overrides,** replacing or extending the profile. Keep one industry taxonomy and one location level.\n6. **Size the pool** with `fetch-entities-statistics` (`entity_type: businesses`, same filters). If it is smaller than the count asked for, relax the most restrictive filter first (the last technology, then the others, then widen the headcount bucket to an adjacent one) and re-check. If it is far larger than needed, add a technology back or narrow the region. For a country-scoped pool, read the per-location breakdown, because the headline count may include other countries.\n7. **Fetch** with `fetch-entities` for businesses with the final filters, plus `business_id` set to the seed's ID from the match with `negate: true`, because a company matches its own profile.\n8. **Show** with `show-sample`.\n\n## Reply\n\n- **Header:** \"Lookalikes for [seed] ([domain])\" and the profile used: industry, headcount bucket, revenue bucket, country or region, technologies. State the size of the pool.\n- **Pattern notes (2-4 bullets):** dominant geography, size concentration, how dense the tech overlap is (tech data is not populated on every company), and any widening you had to apply (\"industry widened because the seed had no LinkedIn category\").\n- **Next steps:** offer the export of all rows, `talent-sourcing` for the people at these companies, or `enrich-company` to go deeper on one.\n\n## Limitations\n\n- There is no similarity model or score. Results are companies that match the rebuilt filters, in fetch order, not ranked by closeness.\n- Technology data is incomplete, so stacking several technologies can shrink the pool faster than expected.\n- If neither industry taxonomy is populated on the seed, the match falls back to size, region and technology, which is looser. Say so.\n- Headcount and revenue are buckets; a seed near a bucket edge can look further from a neighbor than it is.\n- No metro-area filter.\n- Returns companies only, not similar people.\n"
}