Update to Compelling

{
  "description": "Report a bug, rough edge, or feature request for Compelling or this plugin. Use when a Compelling tool call fails unexpectedly, returns wrong data, or the user says they want to report a problem or give feedback about Compelling.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 115
    }
  ],
  "name": "feedback",
  "skill_md_contents": "---\nname: feedback\ndescription: Report a bug, rough edge, or feature request for Compelling or this plugin. Use when a Compelling tool call fails unexpectedly, returns wrong data, or the user says they want to report a problem or give feedback about Compelling.\n---\n\n# Send feedback about Compelling\n\nRoute feedback to the right channel and include enough context to make it actionable.\n\n## Gather context first\n\nBefore filing anything, collect (from the conversation, not by re-running paid tools):\n\n- What the user tried to do, and which tool call failed or misbehaved (tool name + arguments, minus anything sensitive).\n- The exact error text or the unexpected output.\n- The `list_id` / `question_id` involved, if any.\n- Which AI client the user is working in (for example ChatGPT, Codex, Cursor).\n\n**Never include credentials, tokens, or personal contact data (emails, phone numbers) in a report.**\n\n## Channels\n\n- **Plugin or MCP issues** (tool errors, schema problems, skill gaps): open a GitHub issue at\n  https://github.com/seekwhens/compelling-plugin/issues — draft the title and body for the user,\n  then let them review before anything is posted.\n- **Product issues or account questions** (credits, billing, data quality, workspace access):\n  point the user to the in-app support chat at https://app.compelling.ai (bottom-right beacon)\n  or the contact options on https://compelling.ai.\n\n## Draft format for GitHub issues\n\n```\nTitle: <one-line symptom, e.g. \"run_insight returns dispatch_failed for contact email columns\">\n\n**What I did:** <tool + arguments>\n**What happened:** <error/output>\n**Expected:** <what should have happened>\n**Client:** <the AI client in use>\n```\n"
}