asklisted

Ask the second brain in plain words: semantic search over the curated vault with embeddings plus a reranker, returning the smallest relevant slice instead of a corpus dump. Token-cheap. Triggers: "/ask <question>", "what do I have on <topic>", "what did I write about X".
tonydzi/second-brain-starter-kit · ★ 6 · AI & Automation · score 78

Install: claude install-skill tonydzi/second-brain-starter-kit

# /ask — query the Second Brain > 🧒 **When reporting to a non-technical operator:** end with a child-simple "In plain words" recap in their language. Deterministic-first (the operator's token law): RAG retrieves the smallest relevant slice; synthesize ONLY that — never dump the corpus. **Wrong lane?** /ask = semantic MEANING over the curated vault. For exact WORDS inside chats → `/search`; an exact PERSON name → `/find`; a CHAT by name → `/chat` (all 0 tokens, deterministic). Use those when the question isn't conceptual. ## 🖥️ Visual search (a live server — the operator works visually) For interactive eyes-on search: `python "$IMPORTS_ROOT/ask_server.py"` (or `start_ask.bat`) → open `http://127.0.0.1:8770`. It loads e5 + reranker ONCE, after which each query takes ~3s. A search box + filter chips (my writing only / concepts / insights / leads / people / conversations / notes), cards with the rerank score, type, date and a ⏳ staleness flag. CPU by default (does not fight the GPU fleet, holds 0 VRAM); `--gpu` when the GPU is free. This is the GUI for the operator; `--ask` below is for me synthesizing an answer in chat. ## Run (CLI — for synthesizing an answer in chat) `python "$IMPORTS_ROOT/brain_ask.py" "<question>"` Scope with filters (cheaper + sharper): - `--anton` (only the owner's own writing) · `--concepts` (distilled "what I think about X") · `--insights` - `--person <name>` · `--conv` (conversations) · `--leads` (CRM) Returns top-K chunks (chunked + tagged + edi