Update to Altertable

{
  "description": "Delegates analytical questions and follow-up investigations to the Altertable Agent. Use as the default fast path for questions about connected data, metrics, changes, causes, or recommendations when exact SQL control is unnecessary.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 121
    }
  ],
  "name": "ask-altertable",
  "skill_md_contents": "---\nname: ask-altertable\ncompatibility: Requires Altertable MCP server\ndescription: \"Delegates analytical questions and follow-up investigations to the Altertable Agent. Use as the default fast path for questions about connected data, metrics, changes, causes, or recommendations when exact SQL control is unnecessary.\"\nmetadata:\n  author: Altertable\n  requires: \"altertable-mcp\"\n---\n\n# Ask the Altertable Agent\n\nUse the Altertable Agent as the default fast path for analytical questions. It can inspect the governed environment, use semantic models and knowledge, run queries, and return a completed answer without the calling agent coordinating each operation itself.\n\n## Workflow\n\n1. Call `ask` with the user's original question and all constraints that affect the answer.\n2. Return the answer, assumptions, and relevant evidence without repeating the investigation through direct tools.\n3. For a follow-up, pass the returned `chat_id` so the Altertable Agent continues the same investigation. Omit it only for a genuinely separate question.\n\nDo not inspect catalogs or pre-write SQL before `ask` merely to help it. Delegation is valuable because the Altertable Agent performs that work internally.\n\n## Use Direct Tools Instead When\n\n- The user requests exact SQL, raw rows, a query plan, or reproducible query evidence.\n- The task requires a precisely controlled create or update operation.\n- The caller must return Altertable data to another analysis system rather than an interpreted answer.\n- The request concerns ingestion, application instrumentation, or another operation outside analytical Q&A.\n\nWhen a request combines analysis with persistence, use `ask` for the analysis and perform the write only when the user explicitly requested it and the connection has read-write access.\n\n## Guardrails\n\n- Preserve the user's timeframe, timezone, metric definition, and requested scope in the delegated prompt.\n- Do not start a new chat for every follow-up; continuity is the purpose of `chat_id`.\n- Do not present the Altertable Agent's assumptions as established facts.\n- If `ask` reports missing context or ambiguous data, surface that limitation or continue the same chat with the necessary clarification.\n- Use `search_docs` when the question is about Altertable itself rather than the user's data.\n"
}