agentleFS
Sign inStart free
NagiliantNagiliant/Genesis-Legacy-V2/skills/genesis-clarify/SKILL.md

Clarify

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Find and close holes in the master spec before the North Star — resolve ambiguity markers, run a coverage scan, ask high-impact questions, and optionally simulate usage scenarios.

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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 77 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:

    (--simulate): Run 5–10 usage scenarios against the spec text — for each, trace FRs/ACs and mark PASS (spec handles it) or GAP (it …

    line 25

“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 — Close the Holes

A post-spec review that finds and closes gaps before the North Star. Gate: the specify phase must be accepted (else "Accept the spec first").

Inputs

  • .genesis/project-state.md (mode)
  • .genesis/features/<feature>/spec.md (required), design.md (required)
  • brainstorm-log.md (optional), the constitution
  • approvals/master.json (verify specify accepted)
  • dependencies.json for this feature and its peers (cross-feature coverage check)

Process

  1. Resolve markers. Scan the spec for NEEDS_CLARIFICATION markers; resolve each one at a time (question → impact → suggested answer), updating the spec and removing the marker. (--markers-only stops here.)
  2. Coverage scan across 11 categories, rating each Clear / Partial / Missing: Functional Scope · Domain/Data Model · Interaction/UX · Non-Functional Quality · Integration/Dependencies · Edge Cases · Constraints/Tradeoffs · Terminology · Completion Signals · Assumptions · Cross-Feature Dependencies. (--scan-only reports and stops.)
  3. Ask at most 5 targeted questions per run, prioritized by impact, focused on Partial/Missing categories, each with a recommended answer.
  4. Apply answers one at a time — update the spec immediately after each (refine requirements, add edge cases to FRs, document assumptions, strengthen/add ACs, remove resolved open questions).
  5. (--simulate) Run 5–10 usage scenarios against the spec text — for each, trace FRs/ACs and mark PASS (spec handles it) or GAP (it doesn't). Gaps become new questions or amendments.
  6. Re-run constitution compliance if scope changed (halt on violations).
  7. Present a before/after coverage summary table (+ simulation table if used). Commit; update project-state.md.

Mode differences

Each category is mode-aware: greenfield checks completeness of new capability; brownfield checks new-vs-modified classification, preservation of existing behavior, and scope-boundary explicitness; lowfield checks pipeline-stage and artifact-schema completeness and measurable per-stage gates. Simulation likewise differs — greenfield = standard usage; brownfield = migration paths and backward compatibility; lowfield = pipeline at scale (50+ units), mid-stream entry, stage skipping.

Output

  • Updated .genesis/features/<feature>/spec.md (resolved markers, tightened FRs/ACs, documented assumptions) and a coverage summary in the skill output.

Next step

Run /genesis-northstar.

Natural language triggers

- "clarify the spec"
- "find holes in the spec"
- "simulate the 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