菜单
Use when making changes that should be committed. Enforces atomic commits, meaningful messages, and clean history.
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
Use when evaluating whether a proposed change fits the existing architecture. Prevents layer violations, dependency cycles, and accidental coupling.
Use when the user wants a code review instead of implementation. Prioritizes correctness bugs, behavioral regressions, missing tests, and risky assumptions.
Use when reviewing documentation for accuracy, completeness, and alignment with source code. Catches doc-code drift before it confuses readers.
Use when investigating slow execution, high memory usage, or excessive token consumption. Systematic measurement before optimization.
Use when improving code structure without changing behavior. Ensures each refactoring step preserves all existing tests.
Use when reviewing code for security vulnerabilities. Covers prompt injection, path traversal, command injection, and agent-specific attack vectors.
| name | git-workflow |
| description | Use when making changes that should be committed. Enforces atomic commits, meaningful messages, and clean history. |
| version | 1.0.0 |
| author | Aixlarity |
| license | Apache-2.0 |
| metadata | {"aixlarity":{"tags":["git","workflow","version-control","commits"],"related_skills":["code-review","tdd"]}} |
Each commit should represent one logical change. If you cannot describe the commit in one sentence, it is too large.
<type>: <description>
<optional body explaining why, not what>
Types: feat, fix, docs, refactor, test, chore.
cargo test. All tests must pass.cargo clippy. No warnings.cargo fmt --check. Code is formatted.git diff --cached. Every changed line should relate to the commit message.--git flag in aixlarity exec auto-commits after the session. Use it only when the task is self-contained.