agentleFS
AdityaRonAdityaRon/claude-code-harness/skills/pr-review/SKILL.md

pr-review

Skill14 starsChanged 14 days agoMITView on GitHub

How to write a PR review, answer review comments, and request review. Use when reviewing a pull request, replying to a reviewer or review thread, deferring a review ask, marking a PR ready, or asking someone to review.

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

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 3

    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 every review and inline thread already on the PR first.

    line 17
  2. Distinctive:

    Before marking ready, reread the diff for: a guarantee the change states (prompt, docstring, comment, PR body) that some branch breaks, or …

    line 44
  3. Distinctive:

    Never escalate a PR as needing approval before reviewing it.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 178 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

Reviews and review threads

Writing a review

  • The repo's own review rules win. If the target repo records a review format (for example .claude/rules/pr-and-review.md), read it from origin/main and follow it; a session launched outside the repo never auto-loads it. The shape below is the fallback for a repo with none.
  • Shape: open on the sources actually read, not the diff. Bold lead-ins for what you chased down, each citing file:line. Asks numbered, ranked, non-blocking; "Nit:" for trivia; label what is inherited, not introduced. Close "Net: approving".
  • Read every review and inline thread already on the PR first. Leave out what another reviewer raised; where you would add to it, reply on their thread instead. A finding raised twice costs the author a second answer.
  • An ask the diff cannot be edited to satisfy is a rollout note for the ticket.
  • Edit a review in place to keep APPROVED (gh api -X PUT .../reviews/<id>); trim rather than re-post. A review submitted with an empty body cannot be edited, so post the review before any bodiless approval.

Announcing a review

  • The review on GitHub is the answer. Restating it in Slack (approved, no asks, the SHA, CI) puts the same message in two places, and the copy can go stale.
  • Slack carries only what GitHub can't: a decision, merge order, a hold, a question that is not on the PR, or a review not posted yet. Anything else gets a reaction on the request, an approval announcement included: the check mark on the message that asked is the announcement. comms-hub's gate turns a message that only restates into one.

Answering a review

  • Answer ON the PR. A pushed fix, an edited PR body, or a chat message does not answer a reviewer.
  • A deferral needs both channels: its thread, and where the work is tracked now.
  • Disagree with evidence and a conclusion, not with the question back.

Requesting review

  • Before marking ready, reread the diff for: a guarantee the change states (prompt, docstring, comment, PR body) that some branch breaks, or a test asserting that gap; a parse-and-reserialize path that can lose values (integers above 2^53); prose and code that disagree. Mutate the tests the PR adds. An adversarial /code-review is a full extra pass: offer it in the handoff, run it only when asked.
  • Ready for review implies assigning the reviewer.
  • One terse request for every open PR.
  • Never escalate a PR as needing approval before reviewing it.

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.