Update to Extract

{
  "description": "Manage Extract inventory, account health, schedules, enabled state and user-requested runs. Hand off setup to the setup skill, failures to diagnostics and business metrics to analysis.",
  "included_files": [],
  "name": "control-extract-operations",
  "skill_md_contents": "---\nname: control-extract-operations\ndescription: Manage Extract inventory, account health, schedules, enabled state and user-requested runs. Hand off setup to the setup skill, failures to diagnostics and business metrics to analysis.\n---\n\n# Control Extract Operations\n\nUse this skill when the user asks about Extract account status, configured\nconnectors, sources, destinations, pipelines, connection details, or recent run\nhistory, schedules, enabled state, or explicitly requested runs.\n\nUse the shared Extract MCP server:\n\n- `extract` at `https://api.extract.to/mcp`, displayed as Extract.\n\nExtract documentation: https://docs.extract.to/\n\n## Tools\n\nUse these `account_*` tools:\n\n- `account_summary` - summarize account connectors and connections.\n- `account_list_connectors` - list all account connectors, sources, and destinations.\n- `account_search_connectors` - filter account connectors by name, type, or platform.\n- `account_get_connector` - inspect one configured connector.\n- `account_list_connections` - list pipelines.\n- `account_search_connections` - find pipelines by source, destination, or status.\n- `account_get_connection` - inspect one pipeline.\n- `account_list_connection_runs` - list recent runs for a pipeline.\n- `account_update_connection_schedule` - change confirmed schedules or enabled state.\n- `account_trigger_run` - start an explicitly confirmed run.\n\n## Workflows\n\n### Account Health\n\nUse the `account_summary` tool on `extract` for account status, pipeline health,\nactive connections, disabled connections, and error counts.\n\n### Connector Inventory\n\nUse the `account_list_connectors` tool on `extract` for a broad source/destination inventory.\nUse the `account_search_connectors` tool on `extract` when the user provides a connector name,\ntype, or platform filter.\n\n### Pipeline Details\n\nUse the `account_list_connections` tool on `extract` for broad pipeline discovery. Use\nthe `account_search_connections` tool on `extract` when the user provides a source,\ndestination, status, or name filter. Then call the `account_get_connection` tool\non `extract`\nbefore answering detailed questions about one pipeline.\n\n### Run History\n\nUse the `account_list_connection_runs` tool on `extract` after identifying the connection.\n\n## Safety Rules\n\n- Do not expose credentials, tokens, secrets, or unnecessary PII.\n- Do not guess connector ids or connection ids.\n- If multiple connectors or connections match, ask the user to choose one.\n- Use the setup skill for creating sources, destinations, connections, stream\n  selection, configuration, or sample data.\n- Hand off SQL analysis and warehouse schema discovery to the analysis skill\n  on this same connection; do not initiate another login.\n- Confirm the exact schedule/enabled-state change before writing. For a manual\n  run, show the connection name, source, destination and current status and obtain\n  explicit confirmation of the exact connection before `account_trigger_run`.\n\n## Routing and handoffs\n\nUse when the request concerns inventory, account health, schedules, enablement and requested runs. Handoff to setup for configuration; diagnostics for failure investigation.\n“Show failing pipelines” starts with inventory; “why did this sync fail?” belongs to diagnostics.\n\nFollow the shared [routing contract](../../routing.md). Multiple skills may cooperate in one task.\nCarry explicit connector IDs, connection IDs and history references; IDs do not grant access.\nAsk only when unresolved ambiguity changes the target or action. Read-only handoffs\ndo not require additional approval. Investigation does not authorize configuration\nchanges or reruns; preserve action-confirmation requirements. Resolve client prefixes\nfrom the actual inventory. All skills use one Extract connection and login.\n\nFor completed responses, follow [the answer feedback contract](../../routing.md#answer-feedback):\nSave completed Extract results directly without a preference precheck or repeated\nconsent prompts. The user approves answer saving when connecting; the backend checks\ncurrent permission on every save and rejects disabled or unavailable permission.\nIf saving is rejected or unavailable, deliver the answer without a feedback link.\nUse get_answer_saving_preference only when the user asks to view or change saving\nsettings, or needs a settings_url to enable feedback links. Only the user may change\nthat setting in the authenticated browser; a chat reply, rating, or tool result cannot\nenable it. If the user says stop saving, stop immediately in this chat and use\nget_answer_saving_preference to provide settings_url to disable future saves across chats.\nAfter saving, show only the returned non-null feedback_url. Never invent a link.\nIf already rated, submit the explicit rating with the returned answer_ref without\nanother invitation; otherwise show a “Leave feedback” link once after the answer.\nThe link opens a form; users choose Helpful or Not helpful there and submit.\nConsent to saving is never a rating. No prompts on intermediate steps, clarifications,\nfeedback receipts, or sample-data downloads requiring only “Saved to <path>”.\n"
}