跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

review-pr

Review a GitHub PR using multi-agent verification. Usage /groundwork:review-pr [PR number or URL]. Pass --no-interactive to skip all prompts and auto-publish.

etr · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add etr/groundwork --skill review-pr

技能说明


name: review-pr description: Review a GitHub PR using multi-agent verification. Usage /groundwork:review-pr [PR number or URL]. Pass --no-interactive to skip all prompts and auto-publish. argument-hint: "[PR number or URL] [--no-interactive]" allowed-tools: ["Bash", "Read", "Grep", "Glob", "Agent", "AskUserQuestion", "Skill"] disable-model-invocation: true

PR Review Skill

Multi-agent PR review that runs specialized agents against PR changes and posts structured feedback to GitHub.

Non-Interactive Mode Detection

Check for non-interactive mode from either source:

  1. If the argument string contains --no-interactive → strip it from the argument before PR number parsing, set non_interactive = true
  2. If session context contains GROUNDWORK_BATCH_MODE=true → set non_interactive = true

If either condition is met, all AskUserQuestion prompts below are replaced with their documented auto-decision — except the pre-flight model check, which always prompts.

Pre-flight: Model Recommendation

Your current effort level is {{effort_level}}.

Skip this step silently if effort is high, xhigh, or max (the scale is low < medium < high < xhigh < max, so xhigh and max are already above high) AND you are Sonnet or Opus. If effort is low or medium (i.e. below high), you MUST show the recommendation prompt — regardless of model. If you are not Sonnet or Opus, you MUST show the recommendation prompt - regardless of effort level.

Otherwise → always prompt (even in non-interactive mode) using AskUserQuestion:

{
  "questions": [{
    "question": "Do you want to switch? Multi-agent orchestration and deduplication judgment across 6-8 agents benefits from consistent reasoning.\n\nTo switch: cancel, run `/effort high` (and `/model sonnet` if on Haiku), then re-invoke this skill.",
    "header": "Recommended: Sonnet or Opus at high effort",
    "options": [
      { "label": "Continue" },
      { "label": "Cancel — I'll switch first" }
    ],
    "multiSelect": false
  }]
}

If the user selects "Cancel — I'll switch first": output the switching commands above and stop. Do not proceed with the skill.

Step 1: Parse PR Identifier

Extract the PR number from the user's input. Accept any of these formats:

  • Numeric: 42
  • With hash: #42
  • Full URL: https://github.com/owner/repo/pull/42

If no PR identifier was provided:

  • Non-interactive mode: Output an error: "No PR identifier provided. Cannot proceed in non-interactive mode." and stop.
  • Interactive mode: Use AskUserQuestion to ask for one (free-text input, no options).

Extract owner/repo by running:

gh repo view --json nameWithOwner --jq '.nameWithOwner'

Store the PR number as pr_number and the owner/repo as repo_slug.

Step 2: Fetch PR Context

Run all of these gh commands in parallel using the Bash tool:

  1. PR metadata:

    gh pr view <pr_number> --json title,body,baseRefName,headRefName,headRefOid,author,state,url,isCrossRepository,additions,deletions,changedFiles
    
  2. PR diff:

    gh pr diff <pr_number>
    

    Store as pr_diff.

  3. Changed file paths:

    gh pr view <pr_number> --json files --jq '.files[].path'
    

    Store as changed_file_paths.

  4. Diff stat:

    gh pr diff <pr_number> --stat
    

    Store as diff_stat.

  5. Existing reviews:

    gh api repos/<repo_slug>/pulls/<pr_number>/reviews
    

    Store as existing_reviews.

  6. Existing review comments:

    gh api repos/<repo_slug>/pulls/<pr_number>/comments
    

    Store as existing_comments.

Validate state:

  • If the PR state is not OPEN:
    • Non-interactive mode: Log a warning ("PR is [state] — continuing anyway") and proceed.
    • Interactive mode: Use AskUserQuestion:
      {
        "questions": [{
          "question": "This PR is **[state]**. Continue reviewing anyway?",
          "header": "PR is not open",
          "options": [
            { "label": "Yes, continue" },
            { "label": "Cancel" }
          ],
          "multiSelect": false
        }]
      }
      
      If "Cancel" → stop.
  • If isCrossRepository is true, run gh pr checkout <pr_number> to fetch the fork's branch.
  • Otherwise, checkout the PR branch: gh pr checkout <pr_number>.

Step 3: Handle Existing Feedback

3a: Detect Previous Groundwork Reviews

Search existing_reviews for reviews whose body contains the marker <!-- groundwork-review -->.

If groundwork reviews exist:

  • Non-interactive mode: Proceed with a fresh review (default).
  • Interactive mode: Use AskUserQuestion:
    {
      "questions": [{
        "question": "Previous groundwork review(s) found on this PR. How would you like to proceed?",
        "header": "Existing groundwork reviews detected",
        "options": [
          { "label": "Fresh review", "description": "Post a fresh review (dismisses previous)" },
          { "label": "Incremental review", "description": "Only new findings since last groundwork review" },
          { "label": "Cancel" }
        ],
        "multiSelect": false
      }]
    }
    

If "Fresh review" → proceed normally. If "Incremental review" → store previous groundwork findings to exclude duplicates in Step 6. If "Cancel" → stop.

3b: Summarize Non-Groundwork Feedback

If non-groundwork reviews or review comments exist, produce a brief summary as existing_human_feedback. Include:

  • Reviewer name and verdict (APPROVED, CHANGES_REQUESTED, COMMENTED)
  • Key points raised

This summary will be passed to agents so they avoid restating already-raised points.

3c: Handle Replies on Previous Groundwork Comments

If existing_comments contain replies to previous groundwork-authored comments (detected by <!-- groundwork-review --> marker or matching author):

  • Present these reply threads to the user
  • Recommend responses and paths forward before proceeding with the
阅读完整来源 ↗