agentleFS
ryanschueryanschue/automated-product-engineer/skills/pr-review/SKILL.md

pr-review

Skill0 starsChanged 27 days agoMITView on GitHub

Review an existing GitHub pull request by number using its remote metadata, exact base, diff, checks, and discussion. Use for a teammate's or explicitly named pull request; use code-review for local branch changes.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use oss-pr, pr-automation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • jtenniswoodSkill

    updates

    Summarize user-facing project updates from the last 7 days, ordered by importance and written as one-sentence "Feature: description" entries. Use when the user says "/updates", asks what changed recently, or wants a concise list of recent features, device support, fixes that users will notice, or other product value.

    Also in 3 projects that use this

  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • +6 more from openchamber

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read references/remote-review-playbook.md for exact remote evidence, review angles, line-comment rules, stale-head handling, and the …

    line 10
  2. Distinctive:

    Read repository instructions and linked product, architecture, design, migration, or incident context.

    line 21
  3. Distinctive:

    Read unresolved human review threads so the review adds new signal rather than duplicating resolved discussion.

    line 22
  4. Distinctive:

    If the head changes during review, refresh the diff and invalidate conclusions tied to the old SHA.

    line 24
  5. Distinctive:

    Only report issues introduced by the pull request.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 179 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

Pull Request Review

Review the pull request GitHub actually contains. Do not substitute the local working diff.

Read references/remote-review-playbook.md for exact remote evidence, review angles, line-comment rules, stale-head handling, and the recommended output structure.

Intake and pushback

Infer the repository, pull request, base, head, intended outcome, and review history from the current task and GitHub before asking. If the pull request cannot be identified or its intended contract remains materially ambiguous, ask for the single missing identifier or decision. When a product owner must clarify expected behavior, provide a short request with the exact PR, observed behavior, disputed case, and decision needed.

Gather authoritative context

  • Fetch the title, body, author, state, base and head refs, exact SHAs, labels, commits, changed files, and check results.
  • Fetch the complete remote diff. Inspect full files and callers locally only when needed to understand a contract.
  • Read repository instructions and linked product, architecture, design, migration, or incident context.
  • Read unresolved human review threads so the review adds new signal rather than duplicating resolved discussion.

If the head changes during review, refresh the diff and invalidate conclusions tied to the old SHA.

Review the change

Check:

  • behavioral correctness and failure handling
  • compatibility across API, schema, type, and persistence boundaries
  • authorization, privacy, and security exposure
  • concurrency, caching, retry, and idempotency behavior
  • architecture fit, reuse, and unnecessary complexity
  • performance risks supported by a realistic workload
  • whether tests prove the new behavior and important negative paths
  • whether migrations, rollout, rollback, and operational notes match the risk

Only report issues introduced by the pull request. Verify every proposed finding against surrounding code and describe a concrete failure scenario.

Output and comments

Lead with actionable findings ordered by severity, each with a precise file and line reference, impact, reproduction conditions, and suggested direction. Follow with a short change summary and any residual test or rollout risk. If no finding survives verification, say so directly.

Post inline comments or submit a GitHub review only when authorized. Keep each comment self-contained and anchor it to the current head. Do not approve, merge, close, or modify the pull request unless explicitly requested.

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.