agentleFS
Cogni-AI-OUCogni-AI-OU/cogni-ai-agent-skills/gh-aw/SKILL.md

gh-aw

Skill4 starsChanged 6 months agoMITView on GitHub

GitHub Agentic Workflows (`gh aw`) operations for repository automation, creating workflows, running coding agents, and auditing workflow runs. You MUST load this skill when working with the `gh aw` command.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 2 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use gh aw to orchestrate GitHub Agentic Workflows for repository automation.

    line 12
  2. Very specific:

    When compiling .md agent definitions into executable .lock.yml GitHub Actions.

    line 17
  3. Distinctive:

    When writing application code that simply uses the OpenAI or Anthropic API directly.

    line 23
  4. Very specific:

    If gh extension install is unavailable or fails (e.g., in environments without GitHub CLI extension support), you can download and run the …

    line 40
  5. Very specific:

    Setup: Use gh aw init to initialize a repository, followed by gh aw new <workflow-name> or gh aw add-wizard.

    line 122
  6. Very specific:

    Execution: Use gh aw run <workflow-name> to execute a workflow or gh aw trial for simulated runs.

    line 124
  7. Very specific:

    Analysis: If a run fails, load the gh-aw-troubleshooting skill to diagnose the root cause using gh aw audit and gh aw logs.

    line 125
  8. Very specific:

    Updating: Run gh aw upgrade to get the latest agent files and apply codemods.

    line 126
  9. Distinctive:

    Always review the changes made by the AI agent, especially considering security and context.

    line 130
  10. Very specific:

    Do not manually edit the generated .lock.yml files.

    line 131
  11. Very specific:

    When asked to create, update, debug, or upgrade GitHub Agentic Workflows, use webfetch to retrieve and read the appropriate instruction …

    line 142

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- markdownlint-disable MD013 MD023 MD031 MD032 -->

gh-aw Skill

Use gh aw to orchestrate GitHub Agentic Workflows for repository automation.

When to Use

  • To initialize, create, update, or run GitHub Agentic Workflows.
  • When compiling .md agent definitions into executable .lock.yml GitHub Actions.
  • To manage MCP (Model Context Protocol) servers and toolsets within a repository's agent configuration.

When Not to Use

  • For standard GitHub CLI operations that don't involve the Agentic Workflows extension (e.g., just listing issues or PRs).
  • When writing application code that simply uses the OpenAI or Anthropic API directly.
  • For troubleshooting a failed workflow run (use gh-aw-troubleshooting instead).

Common Pitfalls

  • Manual Lockfile Edits: Directly editing the .lock.yml file, which will be silently overwritten the next time gh aw compile is run.
  • Skipping Compilation: Changing an agent's .md definition but forgetting to run gh aw compile, causing the CI pipeline to run the outdated version.
  • Missing Extension: Attempting to run gh aw commands on a fresh runner without first executing gh extension install github/gh-aw.

How to Install the Extension

To install the GitHub Agentic Workflows extension for the GitHub CLI, run:

gh extension install github/gh-aw

If gh extension install is unavailable or fails (e.g., in environments without GitHub CLI extension support), you can download and run the installation script:

curl -sL https://raw.githubusercontent.com/github/gh-aw/v0.74.3/install-gh-aw.sh -o install-gh-aw.sh
head -n 50 install-gh-aw.sh # Review the script before executing
bash install-gh-aw.sh

Mindmap of Commands

mindmap
  root((gh aw))
    Setup Commands
      add
        Add workflows
      add-wizard
        Interactively add workflows
      init
        Initialize repository
      new
        Create new workflow
      remove
        Remove workflow files
      secrets
        Manage secrets
      update
        Update workflows
      upgrade
        Upgrade repository
    Development Commands
      compile
        Compile workflows into YAML
      domains
        List network domains
      fix
        Apply automatic fixes
      lint
        Lint workflows
      mcp
        Manage MCP servers
      validate
        Validate workflows
    Execution Commands
      disable
        Disable workflows
      enable
        Enable workflows
      run
        Run workflows on GitHub Actions
      trial
        Run in trial mode
    Analysis Commands
      list
        List workflows
      audit
        Audit workflow runs
      checks
        Classify CI check state
      health
        Show health overview
      logs
        Analyze workflow logs
      status
        Show workflow status
    Utilities
      completion
        Generate shell completion
      hash-frontmatter
        Compute frontmatter hash
      mcp-server
        Run MCP server
      pr
        Pull request utilities
      project
        Create Projects V2 boards

Core Process

  1. Setup: Use gh aw init to initialize a repository, followed by gh aw new <workflow-name> or gh aw add-wizard.
  2. Development: Workflows are markdown files compiled via gh aw compile into GitHub Actions YAML (.lock.yml).
  3. Execution: Use gh aw run <workflow-name> to execute a workflow or gh aw trial for simulated runs.
  4. Analysis: If a run fails, load the gh-aw-troubleshooting skill to diagnose the root cause using gh aw audit and gh aw logs.
  5. Updating: Run gh aw upgrade to get the latest agent files and apply codemods.

What to Avoid

  • Always review the changes made by the AI agent, especially considering security and context.
  • Do not manually edit the generated .lock.yml files; they are intended to be compiled from the markdown workflows.

References

Agentic Workflow Prompts

When asked to create, update, debug, or upgrade GitHub Agentic Workflows, use webfetch to retrieve and read the appropriate instruction prompt from the official repository before proceeding:

Setup docs

Related Skills

  • gh-aw-compile: You MUST load this skill when recompiling Agentic Workflows.
  • gh-aw-troubleshooting: You MUST load this skill to diagnose and fix failing Agentic Workflows.
  • gh-run: You MUST load this skill when working with GitHub Actions workflow runs.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.