agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/clarify/SKILL.md

clarify

Skill2 starsChanged 5 months agoMITView on GitHub

Walk through every open question in a spec and resolve it with the user. Phase 2.5 of the eight-phase workflow. Modeled on github/spec-kit's /speckit.clarify. Run after /specify if any [OQ] tags remain.

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

7 rules. 0 are common, 2 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    If [OQ] count ≥ 3 AND they cluster around one subsystem (interdependent) → invoke grill-me skill (one-at-a-time depth-first interrogation).

    line 19
  2. Very specific:

    If [OQ] items are orthogonal (different subsystems) → batched mode below.

    line 20
  3. Very specific:

    Update the spec with answers.

    line 24
  4. Very specific:

    If an answer is project-shaping (touches the constitution), log it in .claude/memory/decisions/<date>-<slug>.md.

    line 25
  5. Very specific:

    Update spec status to approved if no [OQ] remain.

    line 26
  6. Distinctive:

    Provide a default: Never just ask — propose, then ask "ok or other?".

    line 31
  7. Distinctive:

    Don't invent answers: If a question requires user input, ask.

    line 33

“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

Walk every [OQ] line in a spec and resolve it with the user. Update the spec, log decisions in memory if they're project-shaping.

Process

  1. Read specs/active/<id>-<slug>.md.
  2. Extract every [OQ] line into a list.
  3. Decide mode — Round 5 A2:
    • If [OQ] count ≥ 3 AND they cluster around one subsystem (interdependent) → invoke grill-me skill (one-at-a-time depth-first interrogation).
    • If [OQ] items are orthogonal (different subsystems) → batched mode below.
    • User passed --grill → force grill mode regardless.
  4. Batched mode: present up to 4 questions at a time via AskUserQuestion. Format: question + your proposed default + alternatives.
  5. Grill mode: hand off to grill-me skill which walks the dependency graph one question at a time.
  6. Update the spec with answers; remove [OQ] tags.
  7. If an answer is project-shaping (touches the constitution), log it in .claude/memory/decisions/<date>-<slug>.md.
  8. Update spec status to approved if no [OQ] remain.

Hard rules

  • Batch orthogonal; grill interdependent. A spec with 5 interdependent auth questions deserves grill-me, not 5 batched cards.
  • Provide a default. Never just ask — propose, then ask "ok or other?".
  • Record decisions. Anything non-obvious goes into the memory log.
  • Don't invent answers. If a question requires user input, ask. Don't paper over.
  • AUTOPILOT — both modes degrade to "use recommendations as defaults, surface as [OQ-pending-operator-review] in handoff" when no human is present.

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