Token导航 LogoToken导航TokenDH.com
开发external-servicegithub未标认证来源可访问许可证需确认审计通过

commit提交

Agent Skill

commit 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

238

周安装

10

GitHub Stars

1

下载量

83
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:commit(提交)
来源仓库:https://github.com/idjoo/skills
仓库路径:skills/commit
安装命令:
npx skills add https://github.com/idjoo/skills --skill commit
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/idjoo/skills --skill commit

简介

用于处理 GitHub 仓库、Issue 和 Pull Request 协作信息。

  • 适合围绕仓库状态或代码变更进行整理。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装命令:npx skills add https://github.com/idjoo/skills --skill commit
  • 安装前建议确认权限范围和维护状态。

SKILL.md

Smart Atomic Commits

Analyze workspace changes, split into logical atomic units, and commit with emoji conventional format.

Process

  1. Inspect: Run git status and git diff HEAD to understand changes
  2. Auto-stage: If nothing is staged, git add all modified and new files
  3. Analyze: Identify if multiple distinct logical changes should be split based on:

- Different concerns (unrelated parts of codebase) - Different types (features vs fixes vs refactoring) - File patterns (source vs docs vs config) - Logical grouping (easier to understand separately) - Size (large changes clearer when broken down)

  1. Commit: For each atomic unit, stage relevant files and commit

Commit Format

type(scope)!: emoji description
ComponentRequiredNotes
typeYesConventional commit type
(scope)NoLowercase, hyphenated (e.g., user-auth, api-client). Omit only when truly global
!NoBreaking change indicator
emojiYesAfter the colon, before description
descriptionYesImperative mood, present tense

Constraints: First line under 72 characters. Focus on "why" over "what". Imperative mood ("add" not "added").

Breaking Changes

Add ! after scope/type. Include BREAKING CHANGE footer:

git commit -m "feat(api)!: 💥 change auth response format" \
  -m "BREAKING CHANGE: /auth/login now returns { token, user } instead of { accessToken, refreshToken }"

Commit Types

TypeEmojiDescription
featNew feature
fix🐛Bug fix
docs📝Documentation
style💄Code style (formatting)
refactor♻️Neither fix nor feature
perf⚡️Performance improvement
testAdding/fixing tests
chore🔧Build process, tools
ci🚀CI/CD improvements
revert⏪️Reverting changes

Extended Emoji Reference

Features: 🏷️ types, 💬 text/literals, 🌐 i18n, 👔 business logic, 📱 responsive, 🚸 UX, 🦺 validation, 🧵 concurrency, 🔍️ SEO, 🔊 logs, 🚩 feature flags, 💥 breaking, ♿️ a11y, ✈️ offline, 📈 analytics

Fixes: 🩹 simple fix, 🥅 catch errors, 👽️ external API changes, 🔥 remove code, 🚑️ hotfix, 💚 CI fix, ✏️ typos, 🔇 remove logs, 🚨 linter warnings, 🔒️ security

Refactoring: 🚚 move/rename, 🏗️ architecture, ⚰️ dead code, 🎨 structure/format

Chore: 🔀 merge, 📦️ packages, ➕ add dep, ➖ remove dep, 🌱 seeds, 🧑‍💻 DX, 👥 contributors, 🎉 init project, 🔖 release, 📌 pin deps, 👷 CI system, 📄 license, 🙈 gitignore

Docs: 💡 source comments

Testing: 🤡 mocks, 📸 snapshots, 🧪 failing test

UI/Assets: 💫 animations, 🍱 assets

Database: 🗃️ DB changes

Other: ⚗️ experiments, 🚧 WIP

Examples

feat: ✨ add user authentication system
fix(parser): 🐛 resolve memory leak in rendering process
refactor(api): ♻️ simplify error handling logic
feat(api)!: 💥 change authentication endpoint response format

Split example (one diff, four commits):

feat(solc): ✨ add new version type definitions
docs(solc): 📝 update documentation for new versions
chore(deps): 🔧 update package.json dependencies
test(solc): ✅ add unit tests for new version features

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.58%
按下载量换算30

Claude

32.34%
按下载量换算27

Cursor

21.03%
按下载量换算17

Gemini CLI

8.6%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills