agentleFS
Sign inStart free
opsmillopsmill/infrahub/.agents/skills/reviewing-pull-requests/SKILL.md

reviewing-pull-requests

Skill548 starsChanged 10 days agoApache-2.0View on GitHub

Reviews a pull request in a separate subagent that has not seen this conversation, applying the rules in REVIEW.md. TRIGGER when: this session has just opened a pull request, for example with `gh pr create`; the user asks for a review of a pull request by URL or number; or a hook reports that large changes were pushed to a pull request. DO NOT TRIGGER when: answering existing review comments → addressing-review; watching CI → monitoring-pull-requests.

  • Commits and pushes

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read REVIEW.md at the root of the repository.

    line 18
  2. Distinctive:

    Run the built-in review:

    line 20
  3. Very specific:

    Claude Code: run the code-review skill with the arguments xhigh <pull request>.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Review a pull request with the code review built into the tool you are running in, without the conversation that wrote the change. The pull request is $ARGUMENTS; in Codex, take it from the request that started this skill, or use the pull request of the current branch.

  1. Read REVIEW.md at the root of the repository. Its rules decide what to report and how to rate it.
  2. Run the built-in review:
    • Claude Code: run the code-review skill with the arguments xhigh <pull request>.
    • Codex: find the base branch with gh pr view <pull request> --json baseRefName, or use the branch origin/HEAD points to when gh cannot reach GitHub. Start a new subagent that does not get this conversation, give it the task "Review the changes this branch would merge into origin/<base branch>, following Codex's built-in review instructions in ${CODEX_HOME:-$HOME/.codex}/skills/.system/review-agent/SKILL.md.", and wait for its result. Codex does not offer that skill by name, so the subagent reads the file. The pull request's branch must be checked out, as it is when this session opened the pull request.
  3. Return the findings with the rules in REVIEW.md applied, separating the issues this pull request introduces from older ones. Change no files.

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