Update to ZoomInfo

{
  "name": "recommend-contacts",
  "description": "Get AI-powered contact recommendations at a target company based on your ZoomInfo interaction history. Provide a company name or domain and optionally a use case.",
  "included_files": [],
  "skill_md_contents": "---\nname: recommend-contacts\ndescription: Get AI-powered contact recommendations at a target company based on your ZoomInfo interaction history. Provide a company name or domain and optionally a use case.\n---\n\n# Recommended Contacts\n\nGet ML-ranked contact recommendations at a target company, personalized to your ZoomInfo usage and CRM data.\n\n## Input\n\nThe user will provide via `$ARGUMENTS`:\n- A company name, domain, or ZoomInfo company ID (required)\n- Optionally: a use case — \"prospecting\", \"deal acceleration\", or \"renewal\" (defaults to PROSPECTING)\n- Optionally: how many results they want (defaults to 25, max 100)\n\n## Workflow\n\n1. **Lookup metadata first** — before calling any other MCP tool, use `lookup` to load reference data for any fields relevant to the request. Use the returned `id` values (not display names) in all subsequent API calls. This ensures accurate parameter resolution and result interpretation.\n\n2. **Resolve the company** if the user provided a name or domain:\n   - Use `search_companies` with `companyName` or `companyWebsite` to find the company — use lookup `id` values for any filters.\n   - Extract the ZoomInfo company ID from the result.\n\n3. **Enrich the company** using `enrich_companies` with the resolved `companyId` to get firmographic context (industry, size, revenue, business model). This context is used to interpret the recommendations.\n\n4. **Map the use case** to the correct enum value:\n   - \"prospecting\" or default → `PROSPECTING` (based on contacts you've viewed, copied, or exported on the ZoomInfo platform; has cold-start support)\n   - \"deal acceleration\" or \"new business\" → `DEAL_ACCELERATION` (based on contacts in closed-won CRM opportunities for new business)\n   - \"renewal\", \"growth\", or \"expansion\" → `RENEWAL_AND_GROWTH` (based on contacts in closed-won CRM opportunities for renewals)\n\n5. **Get recommendations** using `get_recommended_contacts` with:\n   - `ziCompanyId`: the resolved ZoomInfo company ID\n   - `useCaseType`: the mapped enum value\n   - `pageSize`: user-specified count or 25\n\n6. **Enrich the top contacts** using `enrich_contacts` on the top 10 results (batch of 10) to get full contact details including email, direct phone, and accuracy scores.\n\n## Output Format\n\n### Target Company\nOne-line summary: [Company Name] — [Industry], [Employee Count] employees, [Revenue], [HQ Location]\n\n### Use Case\nState which use case was used and what it means:\n- **PROSPECTING**: \"Recommendations based on contacts similar to those you've recently viewed, copied, or exported in ZoomInfo.\"\n- **DEAL_ACCELERATION**: \"Recommendations based on contact patterns from your CRM's closed-won new business deals.\"\n- **RENEWAL_AND_GROWTH**: \"Recommendations based on contact patterns from your CRM's closed-won renewal deals.\"\n\n### Recommended Contacts\n\n| Rank | Name | Title | Department | Management Level | Email | Direct Phone | Accuracy | Score |\n|------|------|-------|------------|-----------------|-------|-------------|----------|-------|\n| 1 | | | | | | | | |\n| 2 | | | | | | | | |\n\nFor each contact, use the `meta` field from the recommendation response to explain WHY they were recommended. The meta describes the reference person the recommendation was based on. Present this as a \"Why Recommended\" note below the table or as an additional column.\n\n### Recommendation Analysis\n\nGroup the recommended contacts by pattern:\n- **By Department**: Which departments are most represented? (e.g., \"8 of 25 are in Sales, 6 in Marketing\")\n- **By Seniority**: What management levels dominate? (e.g., \"Heavily weighted toward Director and VP\")\n- **By Function**: What job functions appear most? (e.g., \"Strong signal toward revenue-facing roles\")\n\nUse the resolved lookup values to categorize accurately — do not guess department or management level labels.\n\n### Engagement Priority\n\nRank the top 5 contacts to engage first, with reasoning:\n- Who has the highest combined relevance (recommendation score) and reachability (accuracy score)?\n- Who is the likely entry point vs. the likely decision-maker?\n- Suggested outreach sequence\n\n### Next Steps\n- Use `/zoominfo:enrich-contact` to deep-dive on any specific person\n- Use `/zoominfo:find-buyers` if you need to filter by specific persona criteria beyond what recommendations provide\n- If recommendations are sparse, note that PROSPECTING recommendations improve as you use ZoomInfo more (view, copy, export contacts). DEAL_ACCELERATION and RENEWAL_AND_GROWTH require CRM integration.\n\n### Important Notes on Scores\n- The `score` (general similarity) and `reRankingScore` (propensity-adjusted) are not directly comparable to each other\n- Higher scores indicate stronger fit but do not guarantee response rates\n- Recommendations refresh daily based on your latest platform and CRM activity"
}