agentleFS
ji-hun-gitji-hun-git/how-to-use-ai/skills/clarify-first/SKILL.md

clarify-first

Skill0 starsChanged 7 days agoMITView on GitHub

Prevents misunderstanding before work starts. Use when a request is ambiguous, underspecified, large, or multi-step (for example "build a dashboard", "write the report", "refactor this module"), or when the user's goal, audience, scope or definition of done is unclear. Asks at most three targeted questions with defaults, then restates the goal and done criteria. Skip it when the request is already clear.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Decide whether to ask: Ask only if a wrong guess would change the result in a way that matters (goal, audience, scope, format, constraints, …

    line 13
  2. Distinctive:

    Not doing: anything you are deliberately leaving out

    line 22
  3. Distinctive:

    Surface assumptions: If you proceed on defaults, list the assumptions at the top of your answer and mark with ⚠️ any that would change the …

    line 23
  4. Distinctive:

    When requirements have piled up over many turns and the output keeps missing, stop patching.

    line 27
  5. Distinctive:

    Don't ask about things you can find out yourself by reading the files, docs or data you have access to.

    line 31
  6. Distinctive:

    Don't ask more than three questions, and don't ask when the answer wouldn't change what you do.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 5 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

Clarify first

Models rarely notice ambiguity on their own, and they tend to lock in early assumptions. A few targeted questions before starting are cheaper than redoing the work.

Steps

  1. Decide whether to ask. Ask only if a wrong guess would change the result in a way that matters (goal, audience, scope, format, constraints, data source). If the request is clear, skip to step 3.
  2. Ask at most three questions, the ones with the biggest impact on the result. For each, give a default:
    1. Who will read this? (Default: non-technical managers.)
    2. ... If you don't answer, I'll go with the defaults.
  3. Restate the task in two or three lines before doing it:
    • Goal: what the result is for
    • Deliverable: what you will produce, in what format
    • Done when: how the user will judge it finished
    • Not doing: anything you are deliberately leaving out
  4. Surface assumptions. If you proceed on defaults, list the assumptions at the top of your answer and mark with ⚠️ any that would change the result significantly if wrong.

If the conversation has drifted

When requirements have piled up over many turns and the output keeps missing, stop patching. Consolidate every requirement and decision so far into one prompt and suggest the user start a fresh chat with it.

Don't

  • Don't ask about things you can find out yourself by reading the files, docs or data you have access to.
  • Don't ask more than three questions, and don't ask when the answer wouldn't change what you do.

Evidence

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.