Update to RocketReach

{
  "name": "prospect",
  "description": "Describe your ideal customer in plain English and get a ranked table of decision-makers with verified contact data",
  "included_files": [],
  "skill_md_contents": "---\nname: prospect\ndescription: Describe your ideal customer in plain English and get a ranked table of decision-makers with verified contact data\n---\n\n# Prospect\n\nTurn a plain-English description of an ideal customer into a ranked list of decision-makers with verified contact info, in one flow.\n\nThis runs the full pipeline: search for the right people, rank them, then enrich the best ones. Use build-list instead if the user only wants to browse matches without spending credits.\n\n## Input\n\nThe user describes their ideal customer in plain English.\n\n- Title / management level / department - required (must include at least one)\n- Industry - optional\n- Company Size - optional\n- Location - optional\n\nIf the description is too vague to search well, ask 1-2 quick questions to clarify further.\n\n## Examples\n\n- `/rocketreach:prospect VPs of Sales at Series B SaaS companies in the US`\n- `/rocketreach:prospect Heads of Marketing at EU e-commerce companies with 100-500 employees`\n- `/rocketreach:prospect CTOs at fintech startups in NYC`\n- `/rocketreach:prospect Procurement directors at large manufacturers using SAP`\n- `/rocketreach:prospect SDR leaders at companies using Salesforce and Outreach`\n\n## Workflow\n\n1. **Parse the ICP into search filters.** Use person_search to map to the fields outlined below\n   - Job title → current_title\n   - Management level → management_levels\n   - Department → department\n   - Location → location\n   - Company Industry → company_industry\n   - Company Size → company_size\n2. **Check Credits available.** Call account once. Capture the user's lookup credit balance, person_export issuance, and daily API call limit. Compute the batch cost projection:\n   - Default: 10 candidates enriched = 10 lookup credits (+ 10 person_export credits if issued).\n   - If the projected cost would consume more than the user's available lookup credits, OR if the user is on a free plan, flag this and pause for explicit confirmation before proceeding.\n3. **Discover Candidates.** Call person_search with the parsed filters. Defaults:\n   - page_size: 25 (search broadly; enrich the top 10).\n   - order_by: relevance.\n4. **Preview Candidates.** Present the top 25 candidates as a preview table with name, title, company, location. Restate the credit cost:\n   - Enriching the top 10 candidates will consume 10 lookup credits (+ 10 person_export credits if issued). Your current balance: [N] lookup credits available.\n   - Reply with \"go\" to proceed, \"show me more\" to expand to 25, or specify a number to enrich (1–25).\n   - Pause for confirmation. Do not consume credits before the user responds.\n5. **Batch enrichment.** On confirmation, call person_lookup in parallel for the confirmed candidate set:\n   - Batch size: ≤ 10 concurrent calls.\n   - Track which calls return pending vs immediate complete data.\n   - For pending results, batch the polling: call check_person_status with all pending profile_ids (up to 100 per call) every 3–5 seconds until all complete or a 60-second timeout. Surface any remaining unresolved at the end.\n6. **Rank by ICP fit.** Score each result against the matched criteria:\n\n   Matched Criteria to check:\n   - Job title\n   - Management level\n   - Department\n   - Location\n   - Company Industry\n   - Company Size\n\n   Ranking:\n   - Strong - if more than 75% of the input criteria matches\n   - Good - if more than 50% of the input criteria matches\n   - Partial - if more than 25% of the input criteria matches\n7. **Format the output.** Use the output template below.\n\n## Output\n\nLeads matching: [ICP summary]\n\n| # | Name | Title | Company | Best Work Email (grade) | Best Personal Email (Grade) | Best Phone | ICP Fit |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | | | | | | | Strong |\n| 2 | | | | | | | Good |\n\nBest Email = recommended_professional_email (or recommended_personal_email if no work email), Best Phone = the phones[] entry flagged recommended.\n\nSummary: Found X matches, enriched top Y. Z credits used ([type]).\n\n## Next actions\n\n- `/rocketreach:enrich-person` - drill into one of the resulting leads.\n- `/rocketreach:healthcare-prospect` - when the ICP is healthcare-shaped.\n- `/rocketreach:enrich-company` - look up one of the employer companies in detail.\n- `/rocketreach:build-list` -  for a search-only pass before committing to enrichment credits.\n\n## Notes\n\n- **Host-level prompts during batch.** Each person_lookup call may trigger a per-call permission prompt in the user's AI client (the lookup tools are destructiveHint: true). Most hosts offer an \"allow for this session\" affordance after the first prompt; surface this in the first prompt's narration if the host supports it.\n- **person_export asymmetry.** Plans without person_export credits issued will see the lookup succeed but the export credit silently skipped. The reported cost should reflect what was actually charged.\n- **Pending lookups.** Some lookups take longer than a few seconds to resolve. The batched polling pattern handles this; if any remain unresolved after 60 seconds, surface them as pending in the summary so the user knows to check back.\n- **Search-result quality varies by ICP specificity.** Very broad ICPs (\"any executive\") will produce many low-fit candidates; very narrow ICPs may return < 10 candidates. Iteration Options should propose concrete refinements based on the actual result distribution.\n"
}