agentleFS
Sign inStart free
haojing8312haojing8312/WorkClaw/.agents/skills/workclaw-repo-hygiene-review/SKILL.md

workclaw-repo-hygiene-review

Skill141 starsChanged 7 months agoApache-2.0View on GitHub

Use when reviewing WorkClaw repo hygiene findings from pnpm review:repo-hygiene, classifying candidates, and recommending the smallest safe cleanup batch without deleting files.

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:

    Use this skill to triage repo hygiene findings and turn them into a small, reviewable cleanup recommendation.

    line 9
  2. Very specific:

    Read .artifacts/repo-hygiene/report.json and .artifacts/repo-hygiene/summary.md.

    line 18
  3. Distinctive:

    Stop after recommendation.

    line 22
  4. Distinctive:

    Treat generated, runtime-owned, config-driven, and dynamically discovered files as high risk.

    line 31
  5. Distinctive:

    Prefer compatibility fallbacks or deprecation when removal is not clearly safe.

    line 32
  6. Distinctive:

    Do not perform cleanup actions in this skill.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

WorkClaw Repo Hygiene Review

Overview

Use this skill to triage repo hygiene findings and turn them into a small, reviewable cleanup recommendation. Keep the work read-only.

When to Use

  • pnpm review:repo-hygiene has findings to interpret
  • Temporary artifacts, dead code, duplicates, stale docs, or orphan files need triage
  • A cleanup batch needs to be scoped before any destructive edit

Workflow

  1. Run pnpm review:repo-hygiene.
  2. Read .artifacts/repo-hygiene/report.json and .artifacts/repo-hygiene/summary.md.
  3. Group findings by category and confidence.
  4. Separate high-risk or uncertain items from confirmed cleanup candidates.
  5. Recommend the smallest cleanup batch that is still well supported.
  6. Stop after recommendation; do not delete, move, or rewrite files.

Output Shape

  • Findings grouped by category
  • Confidence and risk noted for each group
  • Smallest cleanup batch recommendation
  • Any follow-up checks needed before execution

Safety Rules

  • Treat generated, runtime-owned, config-driven, and dynamically discovered files as high risk.
  • Prefer compatibility fallbacks or deprecation when removal is not clearly safe.
  • Do not perform cleanup actions in this skill.

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.

Reviews can't be read right now.

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