repo-polish
Skill24 starsChanged 30 days agoMITView on GitHub
Bring one repository to top-tier open-source standard end to end. Use when asked to polish, standardize, or professionalize a repo. Runs the full checklist and delegates to the narrower skills.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- lukashouthoofd/cenekathontheir own version, first seen Nov 8, 2026
- OneByJorah/VirtOfficeword for word, first seen Nov 1, 2026
- maioio/genesis-architecttheir own version, first seen Oct 2, 2026
Other versions3 projects use a version of this.
Word for word · 1
- OneByJorah/VirtOffice★ 24100% same
Edited · 0
None found.
Wrote their own version · 2
- maioio/genesis-architect★ 48same name
- lukashouthoofd/cenekathon★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- dockerizeSkill
- pr-workflowSkill
- readme-writerSkill
- release-checklistSkill
- screenshot-captureSkill
- security-scrubSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Understand it: Read the code and existing docs.
- Distinctive: line 13
Run it: Start it locally with Docker Compose.
- Very specific: line 14
Dockerize: Follow the dockerize skill: Dockerfile, compose file, .env.example, .dockerignore.
- Distinctive: line 15
Demo data: Add a demo mode that needs no real data, so screenshots are safe.
- Very specific: line 16
Screenshots: Follow screenshot-capture.
- Very specific: line 17
README: Follow readme-writer. Every command in it must have been run.
- Very specific: line 19
CI.: Add the caller workflows from the template (ci, docker, screenshots, release).
- Very specific: line 21
Scrub: Run security-scrub. Fix every finding.
- Very specific: line 22
PR.: Follow pr-workflow. Wait for CI green.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
repo-polish
Work on one repository at a time, on a branch named agent/polish. Never push to main.
Steps
- Understand it. Read the code and existing docs. Write down what it does and how it runs. Create or update
AGENTS.md. - Run it. Start it locally with Docker Compose. If it cannot run, document why and stop to ask.
- Dockerize. Follow the
dockerizeskill: Dockerfile, compose file,.env.example,.dockerignore. - Demo data. Add a demo mode that needs no real data, so screenshots are safe.
- Screenshots. Follow
screenshot-capture. Save todocs/screenshots/. - README. Follow
readme-writer. Every command in it must have been run. - Community files. LICENSE, SECURITY.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md, issue and PR templates, CODEOWNERS, dependabot config. Copy missing ones from the template; do not overwrite existing ones.
- CI. Add the caller workflows from the template (
ci,docker,screenshots,release). - Metadata. Repo description, homepage, 8 to 15 topics, social preview image.
- Scrub. Run
security-scrub. Fix every finding. - PR. Follow
pr-workflow. Wait for CI green. Report the PR link.
Done means
Image builds, container is healthy, README quick start works from a clean clone, screenshots are real and scrubbed, CI is green. Paste the real command output as evidence.
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.

