github-polish
Skill2 starsChanged 43 days agoMITView on GitHub
Improve GitHub presentation: profile, profile README, descriptions, topics, homepage URLs, README intros, and consistency. Use when the user asks to make GitHub look better, look put together, or polish their profile/repos.
In this repository5 other files it gives its agents.
- github-checkupSkill
- github-cleanupSkill
- github-fixSkill
- github-recapSkill
- github-todaySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 47
Do not silently edit the default branch for content changes.
- Distinctive: line 48
Do not invent project capabilities.
- Distinctive: line 49
Prefer small, accurate descriptions over marketing fluff.
- Distinctive: line 51
Keep language approachable.
≈ “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.
Files
github-polish
Make the user's GitHub look put together using evidence from their actual repositories.
Preconditions
gh auth statussucceeds.github-agentis on PATH.
Workflow
- Analyze presentation gaps:
github-agent polish github-agent polish --json - For each improvement:
- Infer suggestions only from repository evidence (README preview, language, topics, homepage, code signals).
- Never fabricate features, stack, or impact.
- Apply changes with the correct safety lane:
Metadata (description / topics / homepage)
- Propose exact new values.
- Preview (
github-agent apply-metadata ...without--execute). - Get explicit user approval.
- Apply with
--execute.
Content (README / profile README)
- Create a branch.
- Modify locally.
- Show the diff.
- Get approval.
- Push and open a pull request with
gh.
Rules
- Do not silently edit the default branch for content changes.
- Do not invent project capabilities.
- Prefer small, accurate descriptions over marketing fluff.
- Topics should be real, conventional, and grounded in evidence.
- Keep language approachable; offer technical detail on request.
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
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.

