agentleFS
Sign inStart free
apinizerapinizer/agentnizer-cookbook/.claude/skills/ask/SKILL.md

ask

Skill2 starsChanged 4 months agoMITView on GitHub

Read-only Q&A about the pipeline, your codebase, the team's runs in .state/, or anything in this cookbook. No code changes, no tasks spawned.

75 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 62 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:

    If your question is really a request to *do* something, the answer will nudge you toward /start.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 62 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 — Read-only Q&A

Pure inspection mode. Answer questions about the pipeline, the codebase, or recent runs without spawning agents or writing code.

Usage

/ask "<question>"

Examples:

/ask "What does the planner do when a task is decomposed?"
/ask "What did the team do on task 20260427-1432-hlt?"
/ask "Show me the recent retrospective findings for the worker module."
/ask "Which agent runs first when I do team.sh start?"
/ask "What's the difference between reviewer and review-correctness?"
/ask "Where do I configure the lint command for a module?"
/ask "Why did the developer retry on this task?"

What it reads

In priority order:

  1. .state/ — for questions about in-flight or recent tasks. meta.json, analysis.md, design.md, progress.md, reviews/*.json, tests.md, qa.md, handoffs.jsonl, completed.jsonl.
  2. .claude/ — for questions about the pipeline itself. Agent definitions, skill specs, profiles, hooks, pipeline-workflow.md.
  3. README.md + docs/ — for high-level orientation questions.
  4. Your project source — only if relevant and the question is about your code (not the pipeline). Stays inside the active task's read_allowlist if there is one.

What it does NOT do

  • ❌ Spawn agents
  • ❌ Write code
  • ❌ Touch .state/ (no new tasks, no meta.json edits)
  • ❌ Call team.sh start
  • ❌ Run shell commands that mutate state (git commit, npm install, test runs, etc.)

The skill is tools: Read, Glob, Grep only. Anything that writes is out of scope.

Good questions vs not-so-good

GoodNot so good
"Why did task X fail?""Fix task X" (use /start with bug-shaped phrasing)
"What does the qa agent check?""Run qa on this code" (use /start)
"Show me retry-rate trend""Reduce retries" (use /start)
"Which lessons mention auth?""Add new auth" (use /start)

If your question is really a request to do something, the answer will nudge you toward /start. The planner detects bug / feature / improvement shape from phrasing — no separate slash command needed.

Output

Plain conversational answer with file references — path:line style — when the answer comes from a specific file. The skill never silently fabricates: if the answer isn't in the readable scope, it'll say "this isn't documented in the cookbook; here's where it might be" and let you decide.

Notes

/ask is the lowest-cost way to onboard. New team members run /ask "walk me through what happens between team.sh start and the first analysis.md" and get a 3-paragraph answer that stitches together the right files.

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