Update to Extract

{
  "name": "control-extract-diagnostics",
  "description": "Diagnose failed Control Extract connections, inspect recent failed runs, and trigger manual runs only after explicit user confirmation.",
  "included_files": [],
  "skill_md_contents": "---\nname: control-extract-diagnostics\ndescription: Diagnose failed Control Extract connections, inspect recent failed runs, and trigger manual runs only after explicit user confirmation.\n---\n\n# Control Extract Diagnostics\n\nUse this skill when the user asks why an Extract pipeline failed, wants failed\nor unhealthy connections, asks for run diagnostics, or asks to manually trigger\na connection run.\n\nThe plugin uses only the Control Extract MCP server:\n\n- `control-extract` at `https://api.extract.to/mcp-account`, displayed as Control Extract.\n\nExtract documentation: https://docs.extract.to/\n\n## Tools\n\nUse these `control-extract` tools:\n\n- `search_connections` - find failed, unhealthy, or matching pipelines.\n- `get_connection` - inspect one pipeline before diagnosis or run control.\n- `list_connection_runs` - inspect recent run history.\n- `diagnose_connection` - read failure diagnostics from recent run logs.\n- `trigger_run` - trigger a manual run only after explicit user confirmation.\n\n## Workflows\n\n### Find Failed Connections\n\nUse the `search_connections` tool on `control-extract` with `status=\"ERROR\"` when the user\nasks for failed, failing, broken, or unhealthy pipelines.\n\nIf the user asks why a pipeline failed, identify the exact connection first,\nthen call the `diagnose_connection` tool on `control-extract`.\n\n### Diagnose A Run\n\nUse the `get_connection` or `list_connection_runs` tool on `control-extract` to confirm the\nconnection context before calling `diagnose_connection`.\n\n### Trigger A Manual Run\n\nNever call `trigger_run` until the user explicitly confirms the exact\nconnection to run. Before asking for confirmation, show the connection name,\nsource, destination, and current status with `get_connection`.\n\n## Safety Rules\n\n- Do not expose credentials, tokens, secrets, or unnecessary PII.\n- Use `diagnose_connection` for failure logs; do not invent failure causes.\n- Do not trigger a run based on an ambiguous connection match.\n- Treat `trigger_run` as a user-confirmed operation, even if the tool itself is\n  available.\n"
}