review-pr
Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL
- License 许可
- MIT
- 最近更新
- 2026-09-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- review-pr
- metadata
- { "internal": true }
- description
- Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL
03 SKILL.md 正文
Review PR
Run the ralph.reviewer.yml orchestration loop against a pull request. The loop checks out the PR in an isolated worktree, runs tests, reviews the diff, and produces a structured report.
Usage
/review-pr <PR number or URL>
Accepts: 207, #207, or https://github.com/.../pull/207
Execution
1. Parse the PR argument
Extract the PR number from the argument. Strip # prefix or extract from URL path.
2. Run the reviewer loop
ralph run -H ralph.reviewer.yml -p "Review PR #<N>"
Bash tool settings:
timeout: 600000(10 minutes)run_in_background: true
Use TaskOutput with block: true to wait for completion.
3. Display the report
Read and print .ralph/REVIEW-REPORT.md to the conversation.
If the report file doesn't exist (loop failed before the synthesizer hat), check for and display whatever intermediate files exist:
.ralph/review-scope.md— what was scoped.ralph/review-verification.md— test results.ralph/review-findings.md— review findings
4. Verify cleanup
Check that the review worktree was removed:
ls -d .worktrees/review-<N> 2>/dev/null
- If gone: cleanup succeeded, no action needed.
- If still present: warn the user but do NOT force-remove. Say what's there and let them decide.
Also note the presence of intermediate files (.ralph/review-scope.md, etc.) — they're useful for debugging but the user may want to clean them up later.
Error Handling
| Situation | Action |
|---|---|
| Ralph exits non-zero | Display error output. Suggest re-running with RALPH_DIAGNOSTICS=1 |
| Report file missing | Display intermediate files that do exist (scope, verification, findings) |
| PR argument missing | Ask the user for the PR number |
| PR argument unparseable | Ask the user to provide a bare number, #N, or full GitHub URL |
What This Skill Does NOT Do
- Does NOT validate the PR exists (the scoper hat handles that)
- Does NOT modify any source code (read-only review)
- Does NOT post comments to GitHub
- Does NOT own worktree cleanup (verifies only)
- Does NOT enable diagnostics by default
04 同仓库更多 Skills
ralph-loop
Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.
ralph-hats
Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph/hats/*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.
ralph-docs
Introspect, explain, and improve ralph-jev using the documentation shipped in its repository. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, completion gate, judge evidence, Jev hooks, parallel loops, configuration), debug an unfamiliar failure mode, or propose a code change to the ralph-jev repo. The skill teaches the agent to answer from the repo's docs and source before guessing, and to scope improvements through the documented architecture rather than the local checkout alone.
complex-test-skill
A directory-style test skill for smoke testing
tui-validate
Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.
tui-debug-in-pane
Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.