whiteboard-search

# Whiteboard Search — Searching the user's notes / library Use this skill when the user asks you to find something in their own notes or in a shared library. ## First, distinguish the two kinds of stores - **User Opsidian** (personal vault) — the raw notes the user writes and captures every day. Accessed via the `opsidian_*` tools. Categories: `inbox / daily / topics / projects / insights`. - **Curated Knowledge** (library) — the organized subset the user has explicitly shared via "Share with VTuber > Library". Accessed via the `knowledge_*` tools. **This is the most trustworthy source you have — because the user hand-picked and sent it.** ## Search Ladder If the user's request is ambiguous, try **both** and merge the results: 1. **`opsidian_search(query, max_results=5)`** — keyword search. The fastest, and best at capturing the user's raw intent. 2. If you get 0–1 results or the scores are low → use **`knowledge_search(query, max_results=5)`** for a semantic search on the curated side. 3. For the 1–3 most likely notes, confirm the contents with **`knowledge_read(filename)`** or **`opsidian_read(filename)`**. 4. Don't dump the body as-is — **summarize it in 2–3 sentences** for the user. Include only 1–2 lines of key quotes if needed. ## When the user specifies a category or tag - Category specified ("among my daily notes…") → narrow with `opsidian_browse(category="daily")`, then search within it. - Tag specified ("the ones tagged #API…") → `opsidian_browse(tag="API")`...