agentleFS
paynewang002-osspaynewang002-oss/question-skill/SKILL.md

question

Skill1 starsChanged 49 days agoMITView on GitHub

Apply an intent gate before consequential work. Use when the user explicitly invokes $question or asks to clarify the task before research, creation, modification, or external action.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. 0kim0bos/yam★ 1same name
    2. couimet/my-claude-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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. Distinctive:

    Check five fields against the current request, prior conversation, and available project context:

    line 12
  2. Distinctive:

    Ask only the 1–3 questions whose answers could materially change the work.

    line 46
  3. Distinctive:

    Before receiving the answers, do not start substantive research, create or modify deliverables, or perform state-changing actions.

    line 48
  4. Distinctive:

    After the user answers, run the gate again.

    line 50
  5. Distinctive:

    Do not use the gate to create unnecessary permission checks or repeat questions.

    line 56
  6. Very specific:

    Do not report a numerical score below 95.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Clarify the user's intended outcome before beginning substantive work. Treat “95% understanding” as a workflow gate, not as a statistically calibrated probability.

Intent gate

Check five fields against the current request, prior conversation, and available project context:

  1. Outcome — the problem, result, or decision the user wants.
  2. Deliverable — the answer, plan, file, artifact, operation, or discussion expected.
  3. Scope — the relevant object, time, region, version, inclusions, and exclusions.
  4. Constraints and authority — facts that must not be assumed, actions outside the scope, and actions requiring final user approval.
  5. Success criteria — what must be true for the task to count as complete and how to verify it.

Pass only when all five are clear enough that remaining uncertainty is unlikely to materially change the result, create significant rework, or cause an incorrect or unauthorized action.

If the gate passes

Briefly state:

Intent gate: Passed (procedural understanding ≥95%; not a statistical probability)
Outcome: ...
Deliverable: ...
Scope and boundaries: ...
Success criteria: ...

Then proceed without asking for confirmation merely to restate the task. Preserve any separate approval required before destructive, irreversible, published, submitted, sent, purchased, or externally visible actions.

If the gate does not pass

State:

Intent gate: Clarification needed
Current understanding: ...
Critical gaps: ...

Ask only the 1–3 questions whose answers could materially change the work. Do not ask for information already available in the conversation or project context.

Before receiving the answers, do not start substantive research, create or modify deliverables, or perform state-changing actions. Safe, read-only inspection is allowed only when it helps resolve ambiguity without committing to an interpretation.

After the user answers, run the gate again. If a blocker remains, name the exact unresolved field instead of inventing certainty.

Judgment rules

  • For routine, low-impact missing details, state a reasonable assumption and pass the gate.
  • For exploratory conversation, the intended deliverable may be joint clarification; do not demand false precision before discussion can begin.
  • Do not use the gate to create unnecessary permission checks or repeat questions.
  • Do not report a numerical score below 95. Use only Passed or Clarification needed; the threshold is a behavioral convention.

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.