agentleFS
Sign inStart free
int2t05int2t05/engineering-skills/skills/08-ship/oss-polish/SKILL.md

oss-polish

Skill3 starsChanged 30 days agoMITView on GitHub

Improve repository presentation, contribution paths and applicable website metadata. Triggers on "polish my repo", "开源项目美化".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Verify actual features, license and install commands.

    line 16
  2. Distinctive:

    Check ignore rules, issue/PR templates and CI.

    line 20
  3. Distinctive:

    Verify links and commands.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Open Source Project Polish

When to use

  • Improve repository presentation, contribution paths and applicable website metadata.

Not for: oss-strategy for business strategy; documentation-audit for factual drift.

Steps

  1. Verify actual features, license and install commands; study useful patterns in comparable repositories rather than star-count marketing.
  2. Lead README with usefulness and a tested quick start, platform install, limits, verification and contribution links; avoid redundant story documents.
  3. Check ignore rules, issue/PR templates and CI; prepare accurate About and Topics, applying remote metadata only when authorized.
  4. For an actual website, verify title, description, canonical, social preview, robots and sitemap where applicable; do not build a site solely for SEO.
  5. Verify links and commands; keep distinctive icon direction in the brand reference and preserve existing licensing.

Output: Suggested paths, subject to human audit: README.md; extra contribution or website artifacts need agreed purpose and paths.

Verify

  • README and contribution links work; website and repository metadata distinguish verified facts from remote proposals.

References

  • engineering-principles.md — shared decision boundaries, scope and verification.
  • human-audit.md — document consent, readability and human review.
  • references/badges.md — shields.io templates by category (languages, hosting, license, status, custom).
  • references/scripts/ — collect-site-metrics.py (README metrics), validate-readme.py (README linter, scores 0–100), github_fetcher.py + readme_fetcher.py + config.py (trending-repo research via GitHub API).

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