界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
数据与研究 · SKILL.md

review-pr

review-pr

【数据与研究】Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

Aareal-project / arealApache-2.0

技能说明

GitHub

name: review-pr description: Read-only pull request review workflow with risk analysis, targeted checklists, and Codex subagent consultation.

Review Pull Request

Use this skill when the user asks for a PR review of the current branch or a specific PR.

Inputs

  • Optional PR number
  • Optional --quick to stop after the change analysis phase

Hard Rules

  • Stay read-only.
  • Do not edit files, commit, push, rebase, or change GitHub state.
  • Do not run build, install, or test commands that mutate the environment.
  • Use gh for PR metadata and git diff retrieval.

Reference Files

  • references/review-pr-domains-and-signals.md
  • references/review-pr-templates.md

Workflow

Phase 1: Resolve PR context

  1. Use gh pr view to fetch PR title, body, state, draft status, and changed files.
  2. If no PR exists, stop and report that clearly.
  3. If the PR is closed, stop.
  4. Record the branch name and changed file list.

Phase 2: Change analysis

  1. Classify changed files using references/review-pr-domains-and-signals.md.
  2. Determine the highest overall risk level: CRITICAL, HIGH, MEDIUM, or LOW.
  3. Build a CHANGE_ANALYSIS_REPORT that lists:
    • detected domains/signals
    • risk level
    • affected files
    • related frameworks
    • likely failure modes

If --quick is set, return the change analysis report and stop here.

Phase 3: Review planning

  1. Select the smallest useful set of review passes from references/review-pr-templates.md.
  2. Split by risk area, not by file count.
  3. Always include at least one general logic pass.

Phase 4: Expert consultation

Consult the matching Codex subagents registered in .codex/config.toml when relevant:

  • archon-expert
  • fsdp-expert
  • megatron-expert
  • algorithm-expert
  • launcher-expert

If the Codex runtime supports parallel subagent execution, run independent review passes in parallel. Otherwise, execute them serially.

Phase 5: Final review

Produce findings first, ordered by severity:

  1. CRITICAL
  2. HIGH
  3. MEDIUM
  4. LOW

For every finding, include:

  • file path
  • line number when available
  • why it is a bug, regression, or risk
  • concrete fix direction

What to Ignore

  • Pure style nits with no correctness impact
  • Issues outside the changed scope unless the PR makes them worse
  • Failures that standard linters or formatters would already catch
  • Speculative concerns with no concrete trigger in the diff

Output Shape

Use this structure:

CHANGE_ANALYSIS_REPORT:
- detected_domains: [...]
- detected_signals: [...]
- risk_level: ...
- affected_files: [...]
- related_frameworks: [...]
- identified_risks: [...]

Findings
1. [severity] Title — path:line
   - Problem: ...
   - Fix: ...

Open Questions
- ...

Residual Risk
- ...
我的收藏