Full pipeline: evaluation -> spec -> implementation -> review -> QA
中文简介正在准备中。当前显示原文说明。
Create a pull request from the current branch with structured summary
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Creates a pull request from the current feature branch with a structured summary, test results, and change description. Closes the pipeline loop: init -> build-feature -> create-pr.
/build-feature/create-pr
main or develop -- refuse to create PR from default branchesgit status to check for uncommitted changes -- if any, warn the user and ask whether to commit firstgit log main..HEAD --oneline to get the list of commits that will be in the PRCollect the information needed for the PR description:
git log main..HEAD --oneline -- list of all commits on this branchgit diff main..HEAD --stat -- files changed with line countsnpm test) and capture pass/failnpm run lint) and capture pass/failfeature/dark-mode -> dark-mode)If tests or lint fail, warn the user but allow them to proceed (some PRs are draft/WIP).
Build a structured PR description:
## Summary
[2-4 bullet points describing what this PR does, derived from commit messages]
## Changes
[File-level summary from git diff --stat]
## Test plan
- [x] Tests: [pass/fail] ([count] tests)
- [x] Lint: [pass/fail]
- [ ] [Any manual verification steps if applicable]
git push -u origin [branch-name]gh pr create:
main (or the project's default branch)/code-review for an AI code review"gh pr merge [number]"User: /create-pr
Checking branch state...
Branch: feature/dark-mode (4 commits ahead of main)
Tests: 82 passed, 0 failed
Lint: 0 errors
Creating PR...
PR #42: "feat: add dark mode toggle to settings"
https://github.com/org/repo/pull/42
Next steps:
- Request review from a teammate
- Run /code-review for AI code review
- Merge when ready
wip: commits from build-feature checkpoints, consider squashing them before creating the PR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。
Full pipeline: evaluation -> spec -> implementation -> review -> QA
中文简介正在准备中。当前显示原文说明。
Convenes multiple agents to debate an important decision
中文简介正在准备中。当前显示原文说明。
Discipline skill — systematic debugging process. Use when encountering any bug, debug issue, test failure, broken function, or unexpected behavior, before proposing fixes.
中文简介正在准备中。当前显示原文说明。
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
中文简介正在准备中。当前显示原文说明。
QA + bugfix cycle until it passes
中文简介正在准备中。当前显示原文说明。
Incremental re-specialization — re-scans the project and updates only auto-generated zones in CLAUDE.md and agents
中文简介正在准备中。当前显示原文说明。