wiki-querylisted

# wiki-query Three-tier retrieval: cheap (hot cache) → cheap (index) → expensive (full pages + semantic search). Stop at the first tier that answers the question. Always cite the wiki pages used. ## Pre-conditions 1. Target vault has `wiki/` scaffolding (`hot.md`, `catalog.md` minimum). If not, tell the user the wiki isn't set up; offer the `wiki` skill. 2. Vault is online (`list_vaults`). ## Modes The user may signal a preferred mode: - **quick** — answer from hot.md alone if possible. Bail to standard if hot doesn't cover it. - **standard** (default) — hot → index → 1-3 specific pages → synthesize. - **deep** — hot → index → semantic search across the wiki → 5-10 pages → synthesize → file the answer back as a new wiki page. If the user didn't say, infer: short factual question = quick; "explain X" = standard; "give me everything you know about X (from my wiki)" = deep. **Disambiguation note**: "research X" is ambiguous — it could mean either (a) "tell me what my wiki has about X" (deep wiki-query) or (b) "go find new information about X on the web" (autoresearch). When the user says "research X" alone, ASK which they mean. Don't guess. ## Steps ### Tier 1: hot.md ``` mcp__obsidian-router__get_file({ vault, path: "wiki-meta/hot.md" }) ``` Read it. If the cache contains the answer (the question is covered by the recent activity), answer from hot alone. Cite `wiki-meta/hot.md` as source. Stop. If hot doesn't cover it: don't try to extract anything tangential. Move