agentleFS
Sign inStart free
pierrebelinpierrebelin/claude-code-toolkit/skills/ask/SKILL.md

ask

Skill7 starsChanged 22 days agoMITView on GitHub

Use when the user asks how the product behaves or why (business rule, use case, decision, handler guarantee), or before changing a handler outside the kit's flow. Answers from the knowledge base via `cctoolkit ask`, each fact cited by id.

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

1 rule. 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Never Read a context's rules.md, decisions.md or HISTORY.md whole: read-bounds refuses it, ask --id gives the object.

    line 31

“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 the knowledge base

Answers from the knowledge base (knowledge.root of .claude/kit.config.json). Formats → skills/knowledge-sync/references/knowledge-format.md, opened only when an answer turns on one.

$ARGUMENTS

Levels

Cheapest first; stop at the one that answers.

  1. Map — <root>/INDEX.md, read whole: the contexts, their prefix and summary. Skipped when the question names its context.
  2. Context — cctoolkit ask --context <C>: its use cases and rules, one line each; <root>/<C>/OVERVIEW.md for its vocabulary, lifecycle and neighbours.
  3. Objects — cctoolkit ask "<question>" [--context <C>] [--kind usecase|rule|decision|adr]: ranked cards. Then cctoolkit ask --id <id>[,<id>] for the one to three that answer, whole. An id as the argument → --id at once; a handler name → --handler <Name>; how something changed → --history [--context <C>] [--id <id>].
  4. Source — the code an object names, or the path:line of its observed line: a bounded Read around that line. Only when the base leaves the question open.

Questions that do not depend on each other go in one message.

Reading the output

  • shown N of M, N below M: the budget cut — narrow with --context, --kind or --id.
  • shown 0 of 0: rephrase once with the other vocabulary — the base is written in language.docs, the code in its own names (archive / ArchiveProductCommandHandler). Still nothing: the base does not cover it; say so, offer to look in the code.
  • An object marked observed <level> is deduced from the code, not validated: say so beside the fact, with its source.
  • Exit 1 (no base): say so, propose /cctoolkit:knowledge-sync.

Never Read a context's rules.md, decisions.md or HISTORY.md whole: read-bounds refuses it, ask --id gives the object.

Answer

The answer first, in the user's language; each fact followed by its id (CAT-RM-003), an observed one by its level and source. A rule, its outcome in code (ProductNotPublishedException). Several contexts involved: one line per context.

The base is never written here. The code contradicts an object, or an object is missing → say it, with path:line, and propose /cctoolkit:knowledge-sync <Context>.

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