Update to Grain

{
  "description": "Synthesize patterns across multiple customers using Grain meetings and, when connected, support conversations or customer email. Use for questions about what customers are saying, emerging workflows, needs, feature requests, confusion, bugs, churn signals, topic analysis, or a weekly customer-insights digest. Use where-things-stand instead for one account.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 228
    },
    {
      "relative_path": "references/customer-research.md",
      "size_in_bytes": 3788
    },
    {
      "relative_path": "references/evidence.md",
      "size_in_bytes": 1664
    },
    {
      "relative_path": "references/retrieval.md",
      "size_in_bytes": 3247
    }
  ],
  "name": "voice-of-customer",
  "skill_md_contents": "---\nname: voice-of-customer\ndescription: Synthesize patterns across multiple customers using Grain meetings and, when connected, support conversations or customer email. Use for questions about what customers are saying, emerging workflows, needs, feature requests, confusion, bugs, churn signals, topic analysis, or a weekly customer-insights digest. Use where-things-stand instead for one account.\n---\n\n# Voice of Customer\n\nTurn customer conversations into a defensible cross-customer evidence report. Grain is the primary source; connected support and email sources are optional enrichment.\n\nRead:\n\n- `references/customer-research.md` for source collection, deduplication, categories, trends, and report structure.\n- `references/retrieval.md` for Grain retrieval.\n- `references/evidence.md` for quotations, denominators, confidence, and coverage honesty.\n\n## Workflow\n\n1. Select the mode: topic analysis, signal scan, or weekly digest. Resolve the time window and state its exact dates.\n2. Inventory available sources. Query Grain. Use support or email only when connected; do not block on unavailable optional sources.\n3. Collect targeted customer-facing evidence and build the evidence ledger. Exclude internal discussion unless it contains the customer's own words.\n4. Deduplicate by customer and concept before counting. Spot-check the three highest-frequency findings against source IDs.\n5. Synthesize the findings with unique-customer denominators, exact quotes when available, `Explicit` or `Inferred` labels, source links, and disclosed coverage gaps.\n6. Compare to a previous report only when one is accessible. Otherwise mark the report as a baseline.\n7. Return the report in chat. Save, post, message, or schedule it only after explicit confirmation.\n\nDo not turn one account into a market pattern. Do not treat repeated mentions by one customer as several customers. Keep evidence separate from interpretation and recommendations.\n"
}