jara-r-kjara-r-k/claude-code-skills/skills/github-pr-review/AGENTS.md

claude-code-skills / github-pr-review

AGENTS.md1 starsChanged 46 days agoMITView on GitHub

Structured pull-request review through the gh CLI. Six steps: read PR context → security (OWASP Top 10) → code quality → performance → test coverage → write the review. Findings are graded Critical / Suggestion / Nit, ending in an APPROVE / REQUEST_CHANGES / COMMENT verdict that is submitted only after the user confirms.

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository16 other files it gives its agents.
- agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- examples/AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- .github/workflows/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- skills/figma-handoff/AGENTS.mdAGENTS.md
- skills/gmail-workflow/AGENTS.mdAGENTS.md
- skills/skill-compliance-checklist/AGENTS.mdAGENTS.md
- skills/skill-compliance-checklist/references/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- figma-handoffSkill
- github-pr-reviewSkill
- gmail-workflowSkill
- skill-compliance-checklistSkill

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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

Very specific:
Run the local CI command from the root AGENTS.md and /skill-compliance-checklist skills/github-pr-review/SKILL.md.
line 30

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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

AGENTS.md

skills/github-pr-review/

Purpose

Structured pull-request review through the gh CLI. Six steps: read PR context → security (OWASP Top 10) → code quality → performance → test coverage → write the review. Findings are graded Critical / Suggestion / Nit, ending in an APPROVE / REQUEST_CHANGES / COMMENT verdict that is submitted only after the user confirms.

Key Files

File	Description
`SKILL.md`	`gh` command catalogue, six-step methodology, review template (Overview, Positives, Findings, Test Coverage, Verdict), error table (PR not found, no permissions, diffs > 1,000 lines, failing CI), three examples, `## Important` rules. v1.0.0, ~1,000 words

For AI Agents

Working In This Directory

Hard rule: never run gh pr review without explicit user confirmation — present the summary first.
Security findings are always Critical; performance findings are Critical if they have production impact, otherwise Suggestion.
The template requires at least one Positive.
agents/code-reviewer.md covers similar ground with a different scale (Critical/High/Medium/Low/Nit, empty sections omitted). That omit-empty rule belongs to the agent, not this skill.
The catalogue lists gh pr review <number> bare; actually submitting needs --approve, --request-changes, or --comment (the last two with --body).
Example 2 hard-codes --base main; repos on another default branch (this one uses master) need the base adjusted.
Bump metadata.version on any change to the methodology or output format.

Testing Requirements

Run the local CI command from the root AGENTS.md and /skill-compliance-checklist skills/github-pr-review/SKILL.md.
Manual: review a real PR number; check all six steps run, every finding cites a file and line, and nothing is submitted without confirmation.

Common Patterns

For PRs over 1,000 lines, list files via gh api repos/{owner}/{repo}/pulls/{number}/files and review them one at a time, security-sensitive files first.
Include gh pr checks failures in the review summary.

Dependencies

External

gh CLI, installed and authenticated (gh auth status)

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