agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/ask/SKILL.md

ask

Skill6 starsChanged 2 months agoMITView on GitHub

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".

72 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If a hit is ⚠ STALE, say so and offer to re-verify (per the epistemic-decay layer).

    line 30
  2. Distinctive:

    If retrieval is thin/irrelevant → say so, suggest a sharper query or a filter.

    line 31
  3. Distinctive:

    Keep it tight; end with 🧒 recap.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/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 + edit-aware index); may flag ⚠ STALE on volatile facts >90d.

Answer

  • Synthesize the returned hits into a DIRECT answer; cite the note titles so the operator can open them.
  • If a hit is ⚠ STALE, say so and offer to re-verify (per the epistemic-decay layer).
  • If retrieval is thin/irrelevant → say so, suggest a sharper query or a filter; do NOT pad with guesses.
  • Keep it tight; end with 🧒 recap.

Note

The index is kept fresh by the reindex routine. If results feel stale right after a big import, mention a reindex may be due (brain_embed_update.py) — but don't reindex unprompted.

<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free