pr-oss
Skill9 starsChanged 16 days agoMITView on GitHub
Write or revise a pull request title and description (PR 본문, PR 설명, PR 작성, PR本文) from an approved diff, including OSS contributions. Use before writing or updating a PR title or description, or opening a PR. Pinned to PR OSS v2.2.1.
In this repository56 other files it gives its agents.
- harness/CLAUDE.mdCLAUDE.md
- academic-research-routerSkill
- accessibilitySkill
- adaptive-project-harnessSkill
- anti-slopSkill
- apple-designSkill
- arenaSkill
- astryx-design-systemSkill
- attention-spanSkill
- copywritingSkill
- crash-outSkill
- croSkill
- cybersecurity-skill-routerSkill
- design-isms-referenceSkill
- design-minimal-blue-pitchdeckSkill
- design-source-routerSkill
- design-specSkill
- diagnosing-bugsSkill
- emil-design-engSkill
- external-review-routerSkill
- frontend-designSkill
- gh-address-commentsSkill
- handoffSkill
- humanize-japaneseSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- hyperframes-studioSkill
- impeccableSkill
- implement-changeSkill
- leak-checkSkill
- library-docsSkill
- loop-librarySkill
- media-useSkill
- motion-graphicsSkill
- obsidian-memory-routerSkill
- openpencil-cliSkill
- ponytailSkill
- product-marketingSkill
- project-startSkill
- remove-ai-marksSkill
- requirements-clarificationSkill
- retroSkill
- review-changeSkill
- screenshotSkill
- security-auditSkill
- startup-evidenceSkill
- taste-guided-uiSkill
- team-patternsSkill
- understandSkill
- verification-before-completionSkill
The file
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
- Distinctive: line 6
Before writing or updating a PR description, read PR OSS v2.2.1 in full and apply it only to the already approved diff, the author's intent …
- Very specific: line 12
Use the bundled references/upstream.md only when shasum -a 256 gives the same hash.
- Distinctive: line 14
If no readable source matches the expected hash, hold only that PR description and explain why.
- Distinctive: line 16
Call a test a regression test only when it was shown to fail on the base commit and pass on the change.
- Distinctive: line 18
Keep the repository's contribution/AI policy and existing approval scope.
- Distinctive: line 20
Do not edit the pinned source.
≈ “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
Before writing or updating a PR description, read PR OSS v2.2.1 in full and apply it only to the already approved diff, the author's intent and the repository's PR template.
Source (pinned, never replace with a newer commit): https://raw.githubusercontent.com/taljeon/pr-oss-skill/6931d56c29b2fc31b9c8a113dcdb552f3dc0eb9a/SKILL.md Expected SHA-256: ee38882c95a7293165f228a0bf67a185e18c2ac613f90ff92ee8795579d1adf0
Use the bundled references/upstream.md only when shasum -a 256 gives the same hash. Resolve it relative to this skill folder.
If no readable source matches the expected hash, hold only that PR description and explain why; do not claim the skill was applied.
Call a test a regression test only when it was shown to fail on the base commit and pass on the change. Otherwise describe what it covers, and if no test exercises the changed behavior, say so in Testing.
Keep the repository's contribution/AI policy and existing approval scope. Reading this skill grants no permission to commit, push, open, edit or comment on a PR.
Do not edit the pinned source. Changing the version means updating this file and the bundled reference together.
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.

