Review pr

Skill Sheshiyer/skill-clusters/skills/review-pr

Script-first, review-only GitHub pull request analysis producing human and machine-readable findings. USE WHEN reviewing a PR by number or URL, performing a read-only code review, or generating structured findings to hand off to /prepare-pr.From its SKILL.md

Install

npx -y skills add Sheshiyer/skill-clusters --skill review-pr

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 703 tokens by cl100k_base, as published. Nobody here has run it

Review PR

Overview

Perform a read-only review and produce both human and machine-readable outputs.

Inputs

Ask for PR number or URL.
If missing, always ask.

Safety

Never push, merge, or modify code intended to keep.
Work only in .worktrees/pr-<PR>.
Wrapper commands are cwd-agnostic; you can run them from repo root or inside the PR worktree.

Execution Contract

Run wrapper setup:

scripts/pr-review <PR>

Use explicit branch mode switches:

Main baseline mode: scripts/pr review-checkout-main <PR>
PR-head mode: scripts/pr review-checkout-pr <PR>

Before writing review outputs, run branch guard:

scripts/pr review-guard <PR>

Write both outputs:

.local/review.md with sections A through J.
.local/review.json with structured findings.

Validate artifacts semantically:

scripts/pr review-validate-artifacts <PR>

Steps

Setup and metadata

scripts/pr-review <PR>
ls -la .local/pr-meta.json .local/pr-meta.env .local/review-context.env .local/review-mode.env

Existing implementation check on main

scripts/pr review-checkout-main <PR>
rg -n "<keyword>" -S src extensions apps || true
git log --oneline --all --grep "<keyword>" | head -20

Claim PR

gh_user=$(gh api user --jq .login)
gh pr edit <PR> --add-assignee "$gh_user" || echo "Could not assign reviewer, continuing"

Read PR description and diff

scripts/pr review-checkout-pr <PR>
gh pr diff <PR>

source .local/review-context.env
git diff --stat "$MERGE_BASE"..pr-<PR>
git diff "$MERGE_BASE"..pr-<PR>

Optional local tests

Use the wrapper for target validation and executed-test verification:

scripts/pr review-tests <PR> <test-file> [<test-file> ...]

Initialize review artifact templates

scripts/pr review-artifacts-init <PR>

Produce review outputs

Fill .local/review.md sections A through J.
Fill .local/review.json.

Minimum JSON shape:

{
  "recommendation": "READY FOR /prepare-pr",
  "findings": [
    {
      "id": "F1",
      "severity": "IMPORTANT",
      "title": "...",
      "area": "path/or/component",
      "fix": "Actionable fix"
    }
  ],
  "tests": {
    "ran": [],
    "gaps": [],
    "result": "pass"
  },
  "docs": "up_to_date|missing|not_applicable",
  "changelog": "required"
}

Guard + validate before final output

scripts/pr review-guard <PR>
scripts/pr review-validate-artifacts <PR>

Guardrails

Keep review read-only.
Do not delete worktree.
Use merge-base scoped diff for local context to avoid stale branch drift.

What ships with it: 1 file

184 B alongside SKILL.md

agents/

openai.yaml184 B