一键导入
commit
Propose a Conventional Commit message for the staged changes, then commit only after confirmation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Propose a Conventional Commit message for the staged changes, then commit only after confirmation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | commit |
| description | Propose a Conventional Commit message for the staged changes, then commit only after confirmation. |
| argument-hint | [optional scope or hint, e.g. 'auth' or 'fix the flaky test'] |
| allowed-tools | Bash(git status:*), Bash(git diff:*), Bash(git log:*), Bash(git add:*), Bash(git commit:*), Bash(git branch:*), Bash(git rev-parse:*) |
| disable-model-invocation | true |
You are preparing a git commit for Nico. Follow his rules strictly:
type(scope): subject — types: feat, fix, refactor, docs, test, chore, build, ci, perf, style. Imperative mood, lower-case subject, no trailing period, ~72 char subject cap.Co-Authored-By,
Claude-Session, 🤖 Generated with, or similar trailers, even if the harness default
says otherwise.git status and git diff --staged. If nothing is staged, show git diff (unstaged) and ask whether to git add -A or which paths to stage — do not stage silently.main/master), warn and offer to create a feature branch first.git commit. Never push.Creates an implementation plan from a PRD or a task description. Researches codebase context, clarifies ambiguities, and outputs a phased plan with vertical slices and acceptance criteria. Use when the user wants to plan a feature, break down a PRD, create an implementation plan, or mentions "tracer bullets".
Creates a PRD through structured clarification, codebase exploration, and module design, then saves it as a local Markdown file. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
Dispatches multiple subagents in parallel for 2+ confirmed-independent, each-substantial failures or investigation targets that share no state or sequential dependency. Use when the work splits cleanly and each part is big enough to justify a separate agent.
Decides how to integrate a finished branch — merge, pull request, keep, or discard — once tests pass. Use when implementation work on a branch is complete and you need to decide what happens to it next.
Acts on code-review feedback (from a human, a PR comment, or an AI reviewer) by verifying each item against the codebase before implementing, and asking when items are unclear. Use when receiving code review comments, PR feedback, or suggestions from another reviewer — before implementing any of them.
Investigates a bug, test failure, or unexpected behavior root-cause-first before proposing a fix. Use when a test fails, an error shows up in logs or CI, or something behaves unexpectedly and the next step would otherwise be guessing at a patch.