gh-aw

作者 githubnext已验证

GitHub Agentic Workflows

341
Stars
43
Forks
Go
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/githubnext/gh-aw

快速入门

使用 gh-aw 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

GitHub Agentic Workflows

Agent quick links

Hello fellow agent! Welcome to GitHub Agentic Workflows = Actions + Agent + Safety. Here are some pointers to get you started in using this tool.

GitHub Agentic Workflows (gh-aw) lets developers define AI-powered repository automation in Markdown with YAML frontmatter and run AI agents securely through GitHub Actions. The gh-aw GitHub CLI extension compiles each agentic workflow into a standard GitHub Actions workflow.

Use conventional GitHub Actions for deterministic builds, tests, linting, deployments, and reproducible scripts. Add an agentic workflow when a task needs reasoning or interpretation, such as issue triage, pull-request review, CI failure investigation, documentation maintenance, dependency analysis, or repository reporting. GitHub Agentic Workflows complements existing CI/CD; it does not replace it.

Built-in AI engines include GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, and Pi. Agent jobs are read-only and sandboxed by default, and configured GitHub writes are normally applied through validated safe-outputs jobs with scoped permissions.

[!NOTE] Releases 0.68.4 through 0.71.3 are being retired due to a bug that impacts billing. If you are running one of these versions, please upgrade to the latest release as soon as possible.

Contents

Quick Start

Install the GitHub CLI extension:

gh extension install github/gh-aw

Then follow the GitHub Agentic Workflows quickstart to select an AI engine, add a sample workflow, and run it through GitHub Actions.

How GitHub Agentic Workflows works

An agentic workflow has two parts: YAML frontmatter configures triggers, permissions, tools, and the AI engine; the Markdown body tells the AI agent what to accomplish. The gh aw compile command validates this source and generates the .lock.yml workflow that GitHub Actions executes. Learn how GitHub Agentic Workflows works.

Security and permissions

Security, permissions, and controlled writes are core design concerns. The supported agent-job path defaults to read-only GitHub access and sandboxed execution. Safe outputs buffer configured writes, validate them, and apply them in separate jobs with scoped permissions. These controls are configurable, so workflow authors must review permissions, tools, network access, and generated files before deployment. Learn how GitHub Agentic Workflows handles security and permissions.

Using agentic workflows in your repository requires careful attention to security considerations and careful human supervision, and even then things can still go wrong. Use it with caution, and at your own risk.

Documentation

Use the GitHub Agentic Workflows documentation for these paths:

For AI agents and retrieval tools, use the published agent prompt index, full prompt corpus, and AI-readable project summary.

Contributing

For development setup and contribution guidelines, see CONTRIBUTING.md.

Custom Go linters

To build and test repository custom linters:

  • go test ./pkg/linters/<linter-name>/...
  • go build ./cmd/linters
  • make golint-custom

make golint-custom builds cmd/linters and runs the custom analyzers against ./cmd/... and ./pkg/....

🌍 Community Contributions

Community members whose issues were resolved — updated automatically.

@a-sjogren-accenture (1) @aaronspindler (1) @abillingsley (2) @adam-cobb (1) @adamhenson (2) @adamtasteslikegood (1) @adhikjoshi (1) @ahmadabdalla (1) @ajfeldman6 (1) @AkshatRaj00 (1) @alanpeabody (1) @alcastaneda (1) @AlexanderWert (1) @AlexDeMichieli (1) @alexsiilvaa (2) @alondahari (17) @alvistar (2) @AmoebaChant (1) @anthonymastreanvae (10) @aoxiangtianyu-go (1) @apenab (1) @arabkin (1) @arezero (6) @arthurfvives (8) @Artur- (1) @askpaisa (1) @askpt (1) @astefan (1) @awoisoak (1) @b-dantas (1) @b2pacific (1) @babaakihiro (2) @bartul (1) @bbonafed (23) @beardofedu (1) @benissimo (8) @benvillalobos (12) @blavity-machine-user (1) @blozano-tt (7) @bmerkle (3) @boydj (2) @Bra1nFartz (1) @BrandonLewis (1) @bryanchen-d (23) @bryanknox (1) @bshore-bf (1) @Calidus (8) @camposbrunocampos (2) @carlincherry (1) @carlosflorencio (1) @CatsMiaow (1) @chepa92 (1) @chrisfregly (2) @chrizbo (7) @CiscoRob (2) @ckittel (1) @cknight (2) @clementbolin (1) @cogni-ai-ee (2) @consulthys (3) @Corb3nik (3) @corygehr (20) @corymhall (1) @crmitchelmore (3) @dagecko (1) @Daidanny008 (1) @Dan-Albrecht (1) @Dan-Co (2) @danielmeppiel (6) @danquirk (2) @darwin-gonzales (1) @davidahmann (3) @davidslater (3) @dbudym-cs (1) @DeagleGross (3) @devantler (2) @deyaaeldeen (10) @dfrysinger (2) @dgolombek (1) @dholmes (3) @dhrapson (2) @DimaBir (1) @dkurepa (1) @DogeAmazed (1) @Dongbumlee (2) @doughgle (1) @drehelis (4) @DrPye (1) @dsfaccini (1) @dsibilio (4) @dsolteszopyn (2) @dsyme (35) @duncankmckinnon (1) @eaftan (3) @edburns (1) @edgeq (2) @elika56 (1) @emexelem (1) @enbw-mmattes (1) @eran-medan (1) @ericchansen (1) @ericstj (2) @Esomoire-consultancy-Company (1) @Etienne-M (4) @Evangelink (5) @fbecar22 (2) @fchareyr (1) @FDevTakima (1) @ferryhinardi (1) @flatiron32 (2) @florianbader (1) @fr4nc1sc0-r4m0n (1) @funkymonkeyjam (2) @G1Vh (1) @GandrotulaRajesh (1) @github-actions (11) @github-antoine-brechon (4) @GKersten (1) @glitch-ux (1) @grahame-white (9) @graphaelli (1) @GregoireW (1) @gregsmi (2) @h-no (1) @h3y6e (2) @haavamoa (1) @haolpku (1) @harrisoncramer (2) @heaversm (1) @heiskr (7) @hermanho (1) @holwerda (3) @hpsin (1) @hrishikeshathalye (1) @ianreay (1) @IEvangelist (14) @Infinnerty (1) @insop (1) @ivancea (9) @j-srodka (6) @jamesadevine (4) @JamesNK (4) @JanKrivanek (4) @jaroslawgajewski (27) @JasonYeMSFT (1) @Jasper13006 (1) @jbaruch (1) @jcooklin (1) @jeffhandley (12) @jeremiah-snee-openx (1) @jfomhover (1) @jhamon (2) @jitran (5) @joesturge (1) @johnpreed (5) @johnwilliams-12 (11) @jonathanpeppers (5) @joperezr (1) @JoshGreenslade (2) @joshjohanning (1) @jsalmassy (1) @jsoref (2) @jsquire (1) @jtracey93 (1) @kaovilai (4) @karl-petter-sj (1) @katriendg (1) @kbreit-insight (5) @KGoovaer (1) @kkruel8100 (2) @Knufle (1) @kriptoburak (1) @Krzysztof-Cieslak (1) @kthompson (1) @kubaflo (1) @labudis (2) @ladamski (1) @lecoursen (1) @lilseyi (2) @lindeberg (1) @loganrosen (4) @look (1) @lpcox (7) @ludoviclafole (1) @lukeed (1) @lupinthe14th (3) @m-titov (1) @maikelvdh (2) @mark-hingston (1) @mason-tim (8) @matiloti (4) @mattcosta7 (1) @MatthewBunker (2) @MatthewLabasan-NBCU (2) @MattSkala (4) @MauroDruwel (4) @maxbeizer (1) @maxknv (1) @mcantrell (1) @mdashrraf (1) @MH0386 (1) @mhavelock (1) @michen00 (2) @microsasa (10) @misrarim (1) @mlinksva (1) @mnkiefer (11) @molson504x (2) @Mossaka (3) @mrfelton (5) @mrjf (7) @MrSanchez (1) @mstrathman (1) @mur6 (1) @mvdbos (2) @nestele (2) @neta-vega (3) @NicoAvanzDev (3) @NicolasRannou (1) @nihal467 (1) @Nikhil-Anand-DSG (1) @NikolajBjorner (2) @norrietaylor (8) @not-mksv (3) @octatone (1) @oscarvalenzuelab (1) @PaulAylward2 (1) @peter-hendy (1) @petercort (1) @pethers (1) @pgaskin (1) @pholleran (4) @Phonesis (1) @Pierrci (1) @plengauer (1) @pmalarme (1) @polmichel (2) @ppusateri (1) @praveenkuttappan (1) @PureWeen (10) @qwert666 (1) @r-garcia-de-oliveira (2) @rabo-unumed (4) @racedale (1) @radiantspace (2) @rafael-unloan (1) @rbstp (5) @reggie-k (3) @remypanicker (1) @rhardouin (2) @ricohomewood (1) @rmarinho (1) @romainh-betclic (3) @rspurgeon (4) @Rubyj (3) @ruokun-niu (1) @ryckmansm (2) @salekseev (3) @salmanmkc (1) @samuelkahessay (30) @samus-aran (1) @SanthoshNandha (1) @sbodapati-gfm (1) @seangibeault (2) @seesharprun (4) @sg650 (15) @shawnHartsell (1) @Shazwazza (2) @shiran-gutsy (1) @shubhamtanwar23 (3) @siyo-rms (1) @srgibbs99 (6) @ssulei7 (1) @stacktick (1) @stefankrzyz (1) @steliosfran (3) @stephen2002119 (1) @straub (6) @strawgate (48) @susmahad (3) @swimmesberger (1) @syarihu (1) @szabta89 (3) @tadelesh (1) @Tarekchehahde (2) @theletterf (25) @thi-feonir (1) @timdittler (3) @tinytelly (1) @tobio (1) @tomasmed (1) @tore-unumed (16) @trask (4) @tsm-harmoney (5) @tspascoal (2) @tvu4-wowcorp (1) @tylersmalley (1) @UncleBats (2) @v1v (4) @verkyyi (2) @veverkap (3) @ViktorHofer (3) @virenpepper (1) @vishalagrawal-jisr (2) @whoschek (1) @wizardofosmium (1) @wtgodbe (4) @xirzec (1) @yaananth (1) @Yoyokrazy (2) @yskopets (53) @zarenner (5) @zkoppert (2)

GitHub Agentic Workflows is supported by companion projects that provide additional security and integration capabilities:

  • Agent Workflow Firewall (AWF) - Network egress control for AI agents, providing domain-based access controls and activity logging for secure workflow execution
  • MCP Gateway - Routes Model Context Protocol (MCP) server calls through a unified HTTP gateway for centralized access management
  • gh-aw-actions - Shared library of custom GitHub Actions used by compiled workflows, providing functionality such as MCP server file management

Workshop

[!TIP] Ready to learn GitHub Agentic Workflows hands-on? The Factory Tour Workshop is a self-contained, step-by-step workshop repository designed to teach you how to build, run, and customize agentic workflows from scratch.

常见问题

What is gh-aw?

gh-aw is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by githubnext. GitHub Agentic Workflows. It has 341 GitHub stars.

Is gh-aw safe to use?

Yes. gh-aw passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install gh-aw?

Clone the repository with "git clone https://github.com/githubnext/gh-aw" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is gh-aw written in?

gh-aw is primarily written in Go. It is open-source under githubnext on GitHub, so you can review or fork the full source.

Are there alternatives to gh-aw?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh gh-aw against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情