Token导航 LogoToken导航TokenDH.com
待分类敏感数据github未标认证来源可访问许可证需确认审计异常

auto-push自动推送

Agent Skill

auto-push 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

1,260

周安装

52

GitHub Stars

68

下载量

412
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:auto-push(自动推送)
来源仓库:https://github.com/luongnv89/skills
仓库路径:skills/auto-push
安装命令:
npx skills add https://github.com/luongnv89/skills --skill auto-push
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/luongnv89/skills --skill auto-push

简介

auto-push 强制暂存全部变更并推送到远程仓库,适用于一次性完整交付场景。

  • 适合在确认所有修改属于同一逻辑单元后快速同步,避免分步提交带来的碎片化问题。
  • 执行前必须同步远程分支,防止基于过期代码提交造成历史混乱。
  • 若工作树不清洁,将自动 stash 当前进度,推送后再恢复现场,确保流程无中断。
  • 慎用此技能,误用可能导致敏感修改被意外公开,建议在私有仓库或受控环境中使用。

SKILL.md

Commit and Push Everything

⚠️ CAUTION: Stage ALL changes, commit, and push to remote. Use only when confident all changes belong together.

Repo Sync Before Edits (mandatory)

Before creating/updating/deleting files in an existing repository, sync the current branch with remote:

branch="$(git rev-parse --abbrev-ref HEAD)"
git fetch origin
git pull --rebase origin "$branch"

If the working tree is not clean, stash first, sync, then restore:

git stash push -u -m "pre-sync"
branch="$(git rev-parse --abbrev-ref HEAD)"
git fetch origin && git pull --rebase origin "$branch"
git stash pop

If origin is missing, pull is unavailable, or rebase/stash conflicts occur, stop and ask the user before continuing.

Workflow

1. Analyze Changes

Run in parallel:

  • git status - Show modified/added/deleted/untracked files
  • git diff --stat - Show change statistics
  • git log -1 --oneline - Show recent commit for message style

2. Safety Checks

❌ STOP and WARN if detected:

  • Secrets: .env*, *.key, *.pem, credentials.json, secrets.yaml, id_rsa, *.p12, *.pfx, *.cer
  • API Keys: Any *_API_KEY, *_SECRET, *_TOKEN variables with real values (not placeholders like your-api-key, xxx, placeholder)
  • Large files: >10MB without Git LFS
  • Build artifacts: node_modules/, dist/, build/, __pycache__/, *.pyc, .venv/
  • Temp files: .DS_Store, thumbs.db, *.swp, *.tmp

API Key Validation: Check modified files for patterns like:

OPENAI_API_KEY=sk-proj-xxxxx  # ❌ Real key detected!
AWS_SECRET_KEY=AKIA...         # ❌ Real key detected!
STRIPE_API_KEY=sk_live_...    # ❌ Real key detected!

# ✅ Acceptable placeholders:
API_KEY=your-api-key-here
SECRET_KEY=placeholder
TOKEN=xxx
API_KEY=<your-key>
SECRET=${YOUR_SECRET}

✅ Verify:

  • .gitignore properly configured
  • No merge conflicts
  • Correct branch (warn if main/master)
  • API keys are placeholders only

3. Execute Immediately (No Extra Confirmation)

Present a short summary, then proceed directly when safety checks pass:

📊 Changes Summary:
- X files modified, Y added, Z deleted
- Total: +AAA insertions, -BBB deletions

🔒 Safety: ✅ No secrets | ✅ No large files | ⚠️ [warnings]
🌿 Branch: [name] → origin/[name]

Proceeding now: git add . → commit → push

Do not ask for additional yes/no confirmation after this skill is invoked.

4. Execute

Run sequentially:

git add .
git status  # Verify staging

5. Generate Commit Message

Analyze changes and create conventional commit:

Format:

[type]: Brief summary (max 72 characters)

- Key change 1
- Key change 2
- Key change 3

Types: feat, fix, docs, style, refactor, test, chore, perf, build, ci

Example:

docs: Update concept README files with comprehensive documentation

- Add architecture diagrams and tables
- Include practical examples
- Expand best practices sections

6. Commit and Push

git commit -m "$(cat <<'EOF'
[Generated commit message]
EOF
)"
git push  # If fails: git pull --rebase && git push
git log -1 --oneline --decorate  # Verify

7. Confirm Success

✅ Successfully pushed to remote!

Commit: [hash] [message]
Branch: [branch] → origin/[branch]
Files changed: X (+insertions, -deletions)

Expected Output

On success, the skill outputs a confirmation block:

✅ Successfully pushed to remote!

Commit: abc1234 feat: add login page with OAuth support
Branch: feature/auth → origin/feature/auth
Files changed: 4 (+112, -8)

If safety checks block the push, the skill outputs:

❌ Push blocked — secrets detected

  .env: OPENAI_API_KEY=sk-proj-xxxxx (real key)

Action required: remove or rotate the key, then re-run /auto-push.

Edge Cases

ScenarioHandling
Merge conflict detectedStop; show conflicting files; tell user to resolve conflicts then re-run
Protected branch (main/master)Warn with a 🔴 banner; recommend creating a branch and using a PR instead
Empty commit (nothing staged)Detect with git status; report "nothing to commit" and exit cleanly
No remote configuredReport "no remote origin"; suggest git remote add origin <url>
Push rejected (non-fast-forward)Run git pull --rebase && git push; if rebase fails, stop and report
Pre-commit hook failsSurface hook output; do not retry; ask user to fix the hook issue
Binary or large file (>10 MB)Block and suggest Git LFS; do not stage the file

Step Completion Reports

After completing each major step, output a status report in this format:

◆ [Step Name] ([step N of M] — [context])
··································································
  [Check 1]:          √ pass
  [Check 2]:          √ pass (note if relevant)
  [Check 3]:          × fail — [reason]
  [Check 4]:          √ pass
  [Criteria]:         √ N/M met
  ____________________________
  Result:             PASS | FAIL | PARTIAL

Adapt the check names to match what the step actually validates. Use for pass, × for fail, and to add brief context. The "Criteria" line summarizes how many acceptance criteria were met. The "Result" line gives the overall verdict.

Skill-specific checks per phase

Phase: Analyze Changes — checks: Modified files listed, Change statistics available, Recent commit style identified

Phase: Safety Checks — checks: Safety scan, Secret detection, Large file check, Branch warning (main/master)

Phase: Commit — checks: Staging complete, Commit message conventional, No merge conflicts

Phase: Push — checks: Push success, Remote branch exists, Final log verified

Error Handling

  • git add fails: Check permissions, locked files, verify repo initialized
  • git commit fails: Fix pre-commit hooks, check git config (user.name/email)
  • git push fails:

- Non-fast-forward: git pull --rebase && git push - No remote branch: git push -u origin [branch] - Protected branch: Use PR workflow instead

Alternatives

If user wants control, suggest:

  1. Selective staging: Review/stage specific files
  2. Interactive staging: git add -p for patch selection
  3. PR workflow: Create branch → push → PR (use /pr command)

⚠️ Remember: Always review changes before pushing. When in doubt, use individual git commands for more control.

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

35.01%
按下载量换算144

Claude

29.61%
按下载量换算122

Cursor

20.02%
按下载量换算82

Gemini CLI

9.28%
按下载量换算38

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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