agentleFS
Sign inStart free
mmaripanguecmmaripanguec/dev-sdd-kit/.claude/skills/clarify/SKILL.md

clarify

Skill2 starsChanged 4 months agoMITView on GitHub

Resolves the ambiguities of a requirement or spec with structured questions (max. 5) and records the answers in the spec's Clarifications section. Use between the F0 triage and F1, when asked to "clarify the requirement", or when a spec has [NEEDS CLARIFICATION] markers.

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quieter, arrange 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.
  • HK-hubSkill

    quieter

    Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.

    Also in 29 projects that use this

  • HK-hubSkill

    arrange

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 14 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • owshq-mecSkill

    layout

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 8 projects that use this

  • +8 more from HK-hub

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 77 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read the requirement (or the spec and its [NEEDS CLARIFICATION] markers) together with the factory context (repos.yaml, current context …

    line 11
  2. Distinctive:

    Only ask what meets ALL THREE: (a) Partial/Absent category, (b) the answer changes scope, design or certification, (c) there is no …

    line 21
  3. Very specific:

    Add/update in the spec the section ## Clarifications → ### Session <today's date> with format - Q: <question> → A: <answer> (decides: …

    line 32
  4. Distinctive:

    If no spec exists yet (a requirement prior to /spec-create is being clarified), deliver the summary of decisions so /spec-create …

    line 42

“Common” is measured: kept by at least 6 in 10 of the 77 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: $ARGUMENTS

Step 1 — Ambiguity scan

Read the requirement (or the spec and its [NEEDS CLARIFICATION] markers) together with the factory context (repos.yaml, current context packs, as-is, knowledge/business-rules.md). Assess coverage per category — Clear / Partial / Absent: scope and out of scope · actors and permissions · main and alternative flows · data and entities · business rules · external dependencies · NFRs (volume, latency, availability) · security/privacy/ regulatory · edge cases · measurable success criteria.

Step 2 — Questions (maximum 5)

Only ask what meets ALL THREE: (a) Partial/Absent category, (b) the answer changes scope, design or certification, (c) there is no reasonable default in the loaded context. Priority: scope > security/privacy > UX > technical detail. Format per question: concrete statement + options table (A, B, C… and "Other") with each option's implication in one line. Present the questions one at a time or as a block, whichever the user prefers; everything else is NOT asked: the default is assumed and noted as an assumption.

Step 3 — Record

With the answers:

  1. Add/update in the spec the section ## Clarifications → ### Session <today's date> with format - Q: <question> → A: <answer> (decides: <who>).
  2. Integrate each answer into the corresponding section of the spec (stories, analysis, out of scope…) and remove its [NEEDS CLARIFICATION] marker.
  3. Ambiguities detected but not asked (they exceeded the maximum or had a default): into the Assumptions block of the Analysis section, or as a marker if they block (maximum 3 live markers in the spec).

If no spec exists yet (a requirement prior to /spec-create is being clarified), deliver the summary of decisions so /spec-create incorporates it from F1. Do not modify anything outside the indicated spec.

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