Update to HubSpot

{
  "name": "hubspot",
  "description": "Use when working with HubSpot CRM records to search, summarize, create, update, associate, or analyze objects and properties.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 233
    }
  ],
  "skill_md_contents": "---\nname: hubspot\ndescription: Use when working with HubSpot CRM records to search, summarize, create, update, associate, or analyze objects and properties.\n---\n\n# HubSpot\n\n## Rules\n\n1. Call `get_user_details` first; check object read/write availability.\n2. Clarify scope: object type, owner/team, pipeline, timeframe, stage, and whether writes are requested.\n3. Use `search_properties` for fields, max 5 `keywords`; use `get_properties` for enum values.\n4. Use `search_crm_objects` for records, counts, filters, pagination, and associations; use `get_crm_objects` for known IDs. Do not use deprecated `search` or `fetch`.\n5. Include clickable HubSpot URLs with UTM params for returned records. State filters, totals, pagination, and whether analysis is sampled.\n\n## Writes\n\nBefore `manage_crm_objects`, show exact proposed changes and get approval:\n\n| Object Type | ID | Property | Current Value | New Value |\n|---|---:|---|---|---|\n\nOn the first confirmation, add: `Want to skip confirmations for this chat? Just ask.`\n\nBatch at most 10 objects. Confirm associations explicitly. Do not write inferred data or overwrite user-entered context without clear consent.\n"
}