Token导航 LogoToken导航TokenDH.com
待分类只读github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

569

周安装

23

GitHub Stars

公开资料未说明

下载量

178
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/ralphcrisostomo/nuxt-development-skills
仓库路径:skills/commit
安装命令:
npx skills add https://github.com/ralphcrisostomo/nuxt-development-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/ralphcrisostomo/nuxt-development-skills --skill commit

简介

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

  • 适合在代码审查、分支管理和团队协作中整理变更内容。
  • 可结合仓库状态快速定位问题或生成提交摘要。commit 属于待分类类 Skill,可作为该场景下的辅助能力补充。
  • 安装前需确认是否有网络访问、文件读写和执行命令权限。
  • 注意维护状态,避免对只读或保护分支进行误操作。

SKILL.md

Git Commit Skill

Sensitive File Guard

Before staging, scan git status for sensitive patterns:

  • .env*, *.pem, *.key, *.p12, *.pfx
  • *.tfstate, *.tfvars (with real values)
  • credentials.json, serviceAccountKey.json, *secret*

If a match is found:

  1. Append the missing pattern to .gitignore and stage .gitignore.
  2. If already tracked, warn and suggest git rm --cached <file>.
  3. Never proceed with committing a sensitive file.

Smart Commit Workflow

1. Review & Sensitive File Guard

git status
git diff
git diff --cached
git log --oneline -5

Scan the output against the sensitive patterns above.

2. Auto-stage tracked changes

git add -u

Stage tracked modifications and deletions only. Review untracked files first and stage by name if appropriate.

3. Analyse for multi-concern splitting

Group changed files by directory or feature area. If changes span unrelated concerns (e.g. a bug fix and a new feature), split into separate commits automatically.

4. Generate commit message

  • Infer type: feat, fix, chore, docs, refactor, test, style.
  • Infer scope from the primary directory or feature area.
  • Subject line: imperative voice, under 72 characters.
  • Body (optional): explain "why", not "what".

5. Commit via heredoc

git commit -m "$(cat <<'EOF'
type(scope): subject line

Optional body.

Co-Authored-By: Claude <model> <noreply@anthropic.com>
EOF
)"

Replace <model> with the actual model name (e.g. Opus 4.6, Sonnet 4.6).

6. Handle pre-commit hook failure

Fix the issue, re-stage, and create a new commit. Never use --no-verify. Never amend — the failed commit does not exist.

Worktree Workflow

When working in a git worktree (.claude/worktrees/<name>/):

  1. Smart commit all changes using the workflow above.
  2. Switch to main in the primary working directory.
  3. Squash-merge: git merge --squash <worktree-branch>.
  4. Commit the squashed result with a single well-formed message.
  5. Verify: git log --oneline -5 && git status.
  6. Remove: git worktree remove.claude/worktrees/<name>.

Commit before merging, always merge into main, never delete the branch before merge is confirmed, use --squash for linear history.

Rules

  • Proceed without confirmation — stage, generate message, and commit in one flow.
  • Never commit sensitive files (run the guard first).
  • Never amend a published commit — create a new one.
  • Never force-push main.
  • Never use --no-verify or --no-gpg-sign.
  • Prefer named files over git add -A to avoid staging secrets or noise.

Quick Reference

  • Sensitive File Guard → git add -u → multi-concern split → Conventional Commit via heredoc with Co-Authored-By.
  • Worktree: commit → squash-merge to main → verify → remove.

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

34.67%
按下载量换算62

Claude

31.3%
按下载量换算56

Cursor

17.37%
按下载量换算31

Gemini CLI

8.64%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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