Update to RocketReach

{
  "name": "build-list",
  "description": "Build a list of people or companies by filtering on title, seniority, department, industry, company size, location, and more. Returns a structured table you can export",
  "included_files": [],
  "skill_md_contents": "---\nname: build-list\ndescription: Build a list of people or companies by filtering on title, seniority, department, industry, company size, location, and more. Returns a structured table you can export\n---\n\n# Build List\n\nBuild a targeted list of people (or companies) from RocketReach and return it as a structured table.\n\n## Input\n\nThe user describes who (or what) they want in natural language.\n\n- Natural-language description of who or what to find.\n- Type - auto-detected (people vs companies); ask once if ambiguous.\n- Result count - optional (default 25, max 100).\n\nExamples:\n\n- `/rocketreach:build-list Product managers at Tech companies in Boston, 51-200 employees`\n- `/rocketreach:build-list VPs of Sales at healthcare companies in the US`\n- `/rocketreach:build-list Directors of Engineering at companies using Salesforce`\n- `/rocketreach:build-list cardiologists in Boston`\n- `/rocketreach:build-list companies in Maine, 200-1000 employees (company list)`\n\n## Workflow\n\n1. **Decide people or companies.** Determine whether the user wants people or companies from cues:\n   - \"VPs\", \"managers\", \"leaders\", \"decision-makers\", \"people who…\" → people.\n   - \"Companies using…\", \"firms with…\", \"startups that…\", \"businesses in…\" → companies.\n   - Ambiguous (\"show me everyone in X\") → ask once.\n2. **Parse the request into search filters.** Each filter is an array in the query object:\n\n   For people (person_search):\n   - Titles → current_title\n   - Seniority → management_levels\n   - Department → department\n   - Skills → skills\n   - Education → school / degree\n   - Location → location\n   - Current employer industry → company_industry\n   - Current employer size → company_size\n   - Healthcare → health_npi, health_specialization, health_license, health_credentials\n   - Free-text → keyword\n\n   For companies (company_search):\n   - Identity → name, domain\n   - Classification → industry, sic_code, naics_code\n   - Size → employees, revenue\n   - Location → location\n   - Tech stack → techstack\n   - Competitors (domains) → competitors\n   - Other signals → keyword, company_tag\n\n   Use exclude for any \"but not X\" patterns.\n3. **Run the search.** Call person_search OR company_search with parsed filters. Defaults:\n   - page_size: 25 (configurable up to 100).\n   - order_by: relevance.\n\n   No credits consumed.\n4. **Show the list first, then offer to enrich it if it is a person list.** Present the results as a table using the templates below. Do NOT auto-run lookups on everyone - that spends credits. Ask the user which people (or how many) they want verified contact info for, then run person_lookup on just those, confirming credit type if multiple are active.\n\n## Output - Person List\n\n### Filters applied\n\nShow exactly what was searched on so the user can verify:\n\n| Filter | Value |\n| --- | --- |\n| current_title | Product Manager |\n| company_size | 51-200 |\n| location | Boston |\n\n### Results (people)\n\n| # | Name | Title | Company | Location |\n| --- | --- | --- | --- | --- |\n| 1 | | | | |\n| 2 | | | | |\n\nPerson Search returns preview fields only (name, current_title, current_employer, location, and the RocketReach profile ID). LinkedIn URL is not part of the search preview — it comes back from person_lookup at enrichment.\n\n## Output - Company List\n\n### Filters applied\n\nShow exactly what was searched on so the user can verify:\n\n| Filter | Value |\n| --- | --- |\n| employees | 51-200 |\n| location | California |\n\n### Results (Company)\n\n| # | Name | Domain | Industry | Size |\n| --- | --- | --- | --- | --- |\n| 1 | | | | |\n| 2 | | | | |\n\nCompany Search returns preview fields only (name, domain, industry_str, employee_count, and the RocketReach company ID).\n\n## Next step\n\n- Person list: Enrich the top N → enrich-person on selected people (confirm count + credit type).\n- Company list: Find people there → prospect or build-list (people) on selected domains.\n\n## Notes\n\n- Keep the search step and the lookup step clearly separate so the user controls credit spend.\n- **No credits consumed.** This is the safe entry point for exploration. The list is a preview; enrichment happens elsewhere.\n- **Result truncation.** When Total matching is high (>1000), the top 25 are not a random sample — they're sorted by relevance. Refinement suggestions help users narrow toward the subset they actually want.\n- **Filter values must resolve.** Industry names, tech-stack names, etc. follow RocketReach's taxonomy. If a user requests a filter that doesn't resolve (e.g., a niche industry name), surface that and suggest the closest matching values.\n"
}