agentleFS
phnx-labsphnx-labs/rush-mcp/skills/review-a-pr/SKILL.md

review-a-pr

Skill0 starsChanged 4 days agoMITView on GitHub

Have a Rush cloud agent review a GitHub pull request and report what it would change. Use when someone asks for a code review, a second opinion on a PR, or a check of a PR before merging.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Start the review: Call create_session with the PR URL as repo, a fresh UUID you write yourself as request_id, and a task like: "Review this …

    line 12
  2. Very specific:

    Offer the next step: Ask follow-up questions with send_session_message in the same session.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review a pull request with Rush

  1. Find the pull request. Get its URL. If the person names only a repository, ask which PR. If list_repositories does not list the repository, say the Rush GitHub App does not reach it yet (https://cloud.getrush.ai/console/settings/?section=connections) and stop.
  2. Start the review. Call create_session with the PR URL as repo, a fresh UUID you write yourself as request_id, and a task like: "Review this pull request. Read the diff and the code it touches, run the tests and linters the repo has, and list each problem with its file and line, why it matters and the change you would make, most serious first. Say plainly if you find nothing. Do not push commits or post comments." Add anything the person asked to focus on, such as security or performance. To review several PRs, start one session each.
  3. Wait. A review takes a few minutes: call wait_for_sessions with timeout_seconds: 50 until it settles.
  4. Report. From get_session: the findings, most serious first, each with its file and line, and which tests ran. Do not add findings of your own to Rush's list. On needs_review or failed, say so with the reason.
  5. Offer the next step. Ask follow-up questions with send_session_message in the same session; its task told it not to push. To make the fixes, start a new session with the findings in its task and the PR's branch (/tree/<branch>) as repo for a branch in the same repository; for a PR from a fork, the new session opens its own pull request. Start it only when the person asks.

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.