在独立工作目录中运行多个Claude Code,统一分配开发任务、监控进度、协助恢复停止的会话,并检查PR测试及评审反馈的处理情况。
- 向多个代理分配开发任务
- 查看进度及空闲worktree
- 恢复停止工作的代理
检查代码变更的测试情况及对现有功能的影响,按仓库模板创建PR,并继续处理评审请求、反馈意见和CI检查。
Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and create PR", or any variation of opening/submitting a pull request.
实测评分 未实测
查看安装方法open-pr从事前检查到评审反馈处理,推进代码变更的PR提交。它会确认更改已提交并推送到远程仓库,检查整个仓库的格式、变更涉及部分的现有测试,以及新行为的测试。随后保留.github/PULL_REQUEST_TEMPLATE.md的结构,填写说明,并按规定的标题格式创建PR。
适合需要遵循项目提交规则,或希望同时整理变更内容与测试情况的时候。运行环境充分时,会继续进行功能测试和自我评审。本地无法充分验证时,会注明未能执行的测试,并跟进评审机器人的回复。
使用Git及GitHub CLI工具gh,默认目标分支为dev。评审流程使用相关技能/pr-test、/pr-review和/pr-address。等待机器人评审的时间最长为60分钟,未收到回复时会向用户报告。合并需要人工批准。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。
不计入评分。 由 AI(OpenAI Codex)于 2026年10月23日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
Before opening the PR:
git push -u origin <branch>)This is critical. Before opening the PR, verify:
If you cannot run the full test suite locally, note which tests you ran and which you couldn't in the test plan.
Read the canonical PR template at .github/PULL_REQUEST_TEMPLATE.md and use it verbatim as your PR body:
cat .github/PULL_REQUEST_TEMPLATE.md### Why / What / How### Changes 🏗️### Checklist 📋<!-- ... -->) with actual content; do not leave them in- [ ] until each step is actually completedPR title must use conventional commit format (e.g., feat(backend): add new block, fix(frontend): resolve routing bug, dx(skills): update PR workflow). See CLAUDE.md for the full list of scopes.
Use gh pr create with the base branch (defaults to dev if no [base-branch] was provided). Use --body-file to avoid shell interpretation of backticks and special characters:
BASE_BRANCH="${BASE_BRANCH:-dev}"
PR_BODY=$(mktemp)
cat > "$PR_BODY" << 'PREOF'
<filled-in template from .github/PULL_REQUEST_TEMPLATE.md>
PREOF
gh pr create --base "$BASE_BRANCH" --title "<type>(scope): short description" --body-file "$PR_BODY"
rm "$PR_BODY"
/pr-test to do E2E manual testing of the PR using docker compose, agent-browser, and API calls. This is the most thorough way to validate your changes before review./pr-review to self-review the PR for correctness, security, code quality, and testing gaps before requesting human review.This is common for agents running in worktrees without a full stack. In this case:
/pr-review locally to catch obvious issues before pushing/review on the PR after creating it to trigger the review botgh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews --paginate and the GraphQL inline threads query. The bot typically responds within 30 minutes, but polling lets the agent react as soon as it arrives./review comment, the same budget
/pr-address and /pr-polish use. If nothing has arrived by then, stop
waiting and tell the user the requested review never came. Never block
indefinitely on a bot./pr-address which has a full polling loop with CI + comment tracking# After creating the PR:
PR_NUMBER=$(gh pr view --json number -q .number)
gh pr comment "$PR_NUMBER" --body "/review"
# Then use /pr-address to poll for and address the review when it arrives
Once the review bot or human reviewers leave comments:
/pr-address to address review comments. It will loop until CI is green and all comments are resolved.| Skill | When to use |
|---|---|
/pr-test | E2E testing with docker compose, agent-browser, API calls — use when you have a running workspace |
/pr-review | Review for correctness, security, code quality — use before requesting human review |
/pr-address | Address reviewer comments and loop until CI green — use after reviews come in; it can also post the /review trigger itself if the PR has no review yet |
After the PR is created and review is triggered:
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
在独立工作目录中运行多个Claude Code,统一分配开发任务、监控进度、协助恢复停止的会话,并检查PR测试及评审反馈的处理情况。
利用Sentry测量数据比较变更前后或不同环境的速度与失败率,考虑统计波动,判定加速、减速、未检测到变化或数据不足,并输出比较结果。
收集PR审查意见,推进代码修改、提交、回复及讨论串解决,同时持续检查CI失败、合并冲突和新增评论,跟进直至审查事项处理完成。
反复审查和修复PR,检查未解决的讨论、评论回复、自动检查及合并冲突,并等待延迟到达的评论,将PR整理到可以合并的状态。
审查拉取请求的目的和代码差异,检查正确性、安全性、设计及测试,避免重复已有评论,并将标注严重程度的问题发布到对应代码行。
在运行中的系统上通过浏览器和API验证PR或分支变更,对照界面、接口及存储数据的变化,并附上操作前后截图报告结果。