agentleFS
Sign inStart free
natalinionatalinio/project-second-brain/.claude/skills/ask/SKILL.md

ask

Skill0 starsChanged 25 days agoMITView on GitHub

Answer a question about the project and its subject, grounded in the knowledge base and cited (path#lines or SQL). Use for any factual question about the documents, data, systems, open points, claims or decisions of this project.

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

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read only the line ranges the graph or kb.sections point to.

    line 14
  2. Very specific:

    Every factual statement cites path#Lstart-Lend or the SQL.

    line 20
  3. Very specific:

    Not grounded → "not documented" + a proposed OP (title, owner, impact).

    line 24
  4. Very specific:

    If the graph missed a name that exists in the corpus, add the alias to tools/kb/entities.yaml and say so in one line.

    line 25

“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

Question: $ARGUMENTS (the text typed after the command).

Ground before answering, cheapest step first; stop as soon as the answer is grounded.

  1. Name the objects/concepts in the question. For each, run in the terminal: uv run python tools/kb/graph.py about <name> --limit 8 (unresolved → graph.py find <part>).
  2. Countable / listable → SQL with uv run python tools/ingest/query.py "..." (structured tables, or kb.*: kb.reg_open_points, kb.reg_claims, kb.reg_decisions, kb.catalog, kb.sections, kb.edges). Show the query.
  3. Read only the line ranges the graph or kb.sections point to. Never read a whole note above the abstract threshold (tools/kb/schema.yaml, 40 KB by default).
  4. Text search only if steps 1–3 found nothing.

Answer:

  • ≤ 15 lines unless asked for more. The answer first, then the evidence.
  • Every factual statement cites path#Lstart-Lend or the SQL. Say the evidence level when weaker than primary-doc; add "(extraction unchecked)" for notes with status: extracted. derived-llm / assumed are never stated as fact.
  • What is (observed) and what we intend (design, decisions) go in separate, labelled sentences. Conflicting sources: report both, do not pick.
  • Not grounded → "not documented" + a proposed OP (title, owner, impact). Record it only after the user agrees (/capture).
  • If the graph missed a name that exists in the corpus, add the alias to tools/kb/entities.yaml and say so in one line.

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