commit-by-logic
分析git更改并分次提交,支持从git diff或git staged分析,每次提交都是逻辑上独立的功能
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
分析git更改并分次提交,支持从git diff或git staged分析,每次提交都是逻辑上独立的功能
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Capture a multi-step workflow into a timestamped pipeline memory after trial-and-error sessions. The core output is: (1) the final working commands saved as executable scripts (not bare shell commands), and (2) a structured markdown document separating the clean reproducible pipeline from the detours and pitfalls. Timestamped snapshots live in pipeline_memory/; mature pipelines can be promoted to PIPELINE.md and auto-loaded. Fully environment-agnostic — works for any project, any toolset, any domain. Use when the user finishes a multi-step task, says "保存工作流记忆", "save pipeline memory", "记录一下当前进展", or "/save-pipeline-memory". Takes an optional folder path.
Run Claude Code commands (including /insights, /doctor, custom prompts) via system crontab in non-interactive mode. Use when: (1) setting up daily/weekly automated Claude Code tasks, (2) scheduling reports or analysis via cron, (3) running Claude Code with third-party API backends (DeepSeek, Qwen, etc.) in headless environments, (4) "set up a daily report", "automate this in cron", "schedule insights". Covers: cron PATH setup, third-party API env vars for non-interactive mode, nvm/node auto-discovery, and wechat-reminder integration for notification delivery.
Use when the user wants to *learn* or *understand* a technical concept (an algorithm, a math derivation, an ML architecture, a systems internal) rather than just get a one-shot answer — triggers include "explain X", "teach me X", "help me understand X", or being stuck on a concept while reading a paper or code. Probe the user's level with a few questions FIRST, then teach interactively through a runnable Jupyter notebook with LaTeX derivations and small experiments.
Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.
Record a debugging session's findings into a timestamped markdown file under debug_experience/. Captures problem, root cause, solution, and key learnings in a structured, reusable format. Use when: you've just resolved a non-obvious bug, found an undocumented edge case, encountered an issue that took multiple attempts to fix, or when you say things like "保存调试经验", "save debug experience", "记录这次调试", "/save-debug-experience". Takes an optional folder path as argument.
MCP Notion工具使用指南,包含常见问题解决方案和最佳实践。使用当: (1) 访问Notion数据库view URL出现"URL type view not currently supported"错误, (2) 需要获取数据库schema和表结构信息, (3) 查询数据库中的条目内容, (4) 创建页面时MULTI_SELECT字段值不存在导致失败, (5) 需要更新数据库schema添加新选项, (6) 开发需要集成Notion数据的自动化工作流, (7) query_data_sources/query-database-view返回Business Plan要求错误, (8) 需要在无Business Plan的情况下枚举数据库所有条目。
| name | commit-by-logic |
| description | 分析git更改并分次提交,支持从git diff或git staged分析,每次提交都是逻辑上独立的功能 |
这个工具帮助你分析git更改并将更改分成多个逻辑上独立的提交。支持从git diff(未暂存更改)或git staged(已暂存更改)分析。每个提交都遵循<type>(<scope>): <description>格式。
运行 /commit-by-logic 或 /commit-by-logic [--source diff|staged] [type]
参数说明:
--source diff|staged: 可选,指定分析来源。diff表示分析未暂存更改(默认),staged表示分析已暂存更改type: 可选的提交类型前缀,如feat、fix等。如果不提供,系统会为每个分组自动选择合适的类型。示例:
/commit-by-logic - 分析未暂存更改并分次提交/commit-by-logic --source staged - 分析已暂存更改并分次提交/commit-by-logic --source diff feat - 分析未暂存更改,使用feat作为默认类型/commit-by-logic fix - 分析未暂存更改,使用fix作为默认类型<type>(<scope>): <description>格式的提交消息遵循Conventional Commits规范:<type>(<scope>): <description>
feat: 新功能fix: 修复bugdocs: 文档更新style: 代码格式调整(不影响功能)refactor: 代码重构test: 测试相关chore: 构建过程或辅助工具的变动perf: 性能优化ci: CI配置变更可选的模块或组件名称,如auth、api、ui、config等。
简短描述,使用英文,使用现在时祈使句,首字母不大写,不加句号。
解析用户提供的参数:
--source staged,设置 SOURCE="staged"--source diff,设置 SOURCE="diff"SOURCE="diff"根据分析来源检查状态:
# 检查git状态
git status --porcelain
# 根据SOURCE参数选择分析来源
if [ "$SOURCE" = "staged" ]; then
git diff --cached --name-status
else
git diff --name-status
fi
根据分析来源获取详细的更改信息:
if [ "$SOURCE" = "staged" ]; then
# 分析已暂存更改
git diff --cached --name-only
git diff --cached --stat
else
# 分析未暂存更改(默认)
git diff --name-only
git diff --stat
fi
请按照以下逻辑分析更改并分组:
按文件类型分组:
chore或configdocsteststyle按功能模块分组:
src/auth/, src/api/, ui/, components/等)按更改类型分组:
featrefactor或fix对于每个逻辑分组:
type和scopedescriptiontype(scope): description示例:
feat(auth): 添加用户登录功能fix(api): 修复用户查询接口空指针异常docs(readme): 更新安装说明chore(deps): 升级react到v18在开始提交前,请向我展示:
$SOURCE (diff或staged)等待我的确认后再开始执行提交操作。
对于每个确认的分组:
$SOURCE = "diff"(分析未暂存更改),需要先暂存文件:
git add [文件列表]
$SOURCE = "staged"(分析已暂存更改),文件已暂存,直接提交git commit -m "提交消息" 提交以下文件不应被提交,在分组时自动忽略:
CLAUDE.md、GEMINI.md 等 AI 指令文件core dump 文件)--source diff(默认):分析未暂存的更改(git diff)。适用于正在编辑但尚未暂存的文件。--source staged:分析已暂存的更改(git diff --cached)。适用于已经使用 git add 暂存的文件。--source diff 时,工具会自动暂存每个分组的文件然后提交--source staged 时,文件已经暂存,工具直接提交--source diff 且没有未暂存更改,提示:"No unstaged changes to commit. Use --source staged if you have staged changes."--source staged 且没有已暂存更改,提示:"No staged changes to commit. Use --source diff if you have unstaged changes."--source staged),然后再处理未暂存更改(--source diff)