Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

commit-messages提交消息

Agent Skill

commit-messages 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

291

周安装

12

GitHub Stars

502

下载量

95
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-messages(提交消息)
来源仓库:https://github.com/thedecipherist/claude-code-mastery
仓库路径:skills/commit-messages
安装命令:
npx skills add https://github.com/thedecipherist/claude-code-mastery --skill commit-messages
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/thedecipherist/claude-code-mastery --skill commit-messages

简介

commit-messages 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。

  • 它适用于提交消息规范相关研究,可结合来源仓库和原始 README 核验具体用法。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。
  • 安装前建议确认权限范围和维护状态,避免触发不必要的联网或文件操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Commit Message Skill

Generate consistent, informative commit messages following the Conventional Commits specification.

When to Use This Skill

  • User asks to "commit", "write a commit message", or "prepare commit"
  • User has staged changes and mentions commits
  • Before any git commit command

Process

  1. Analyze changes: Run git diff --staged to see what's being committed
  2. Identify the type: Determine the primary change category
  3. Find the scope: Identify the main area affected
  4. Write the message: Follow the format below

Commit Message Format

<type>(<scope>): <description>

[optional body]

[optional footer(s)]

Types

TypeDescriptionExample
featNew featurefeat(auth): add OAuth2 login
fixBug fixfix(api): handle null response
docsDocumentation onlydocs(readme): add setup instructions
styleFormatting, no code changestyle: fix indentation
refactorCode change, no new feature/fixrefactor(db): extract query builder
perfPerformance improvementperf(search): add result caching
testAdding/fixing teststest(auth): add login unit tests
buildBuild system changesbuild: update webpack config
ciCI configurationci: add GitHub Actions workflow
choreMaintenance taskschore(deps): update dependencies
revertRevert previous commitrevert: feat(auth): add OAuth2

Scope

The scope should be a noun describing the section of the codebase:

  • auth, api, db, ui, config
  • Feature names: search, checkout, dashboard
  • Or omit if change is broad

Subject Line Rules

  • Use imperative mood: "add" not "added" or "adds"
  • Don't capitalize first letter after colon
  • No period at the end
  • Max 72 characters total

Body (when needed)

  • Separate from subject with blank line
  • Explain *what* and *why*, not *how*
  • Wrap at 72 characters
  • Use bullet points for multiple changes

Footer (when needed)

  • BREAKING CHANGE: for breaking changes
  • Fixes #123 to close issues
  • Refs #456 to reference without closing

Examples

Simple feature

feat(search): add fuzzy matching support

Implement Levenshtein distance algorithm for typo tolerance
in search queries. Configurable via FUZZY_THRESHOLD env var.

Bug fix with issue reference

fix(cart): prevent duplicate items on rapid clicks

Add debounce to add-to-cart button and check for existing
items before insertion.

Fixes #234

Breaking change

feat(api)!: change response format to JSON:API

BREAKING CHANGE: API responses now follow JSON:API spec.
All clients need to update their parsers.

- Wrap data in `data` object
- Move metadata to `meta` object
- Add `links` for pagination

Multiple related changes

refactor(auth): consolidate authentication logic

- Extract JWT handling to dedicated service
- Move session management from controller to middleware
- Add refresh token rotation

This prepares for the upcoming OAuth2 integration.

Output

When generating a commit message:

  1. Show the staged changes summary
  2. Propose the commit message
  3. Explain the type/scope choice if non-obvious
  4. Ask if the user wants to proceed or modify

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

32.53%
按下载量换算31

Claude

32.03%
按下载量换算30

Cursor

20.32%
按下载量换算19

Gemini CLI

8.65%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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