Github Agentic Workflows

This is the comprehensive skill for working with GitHub's new agentic workflow system, the markdown-based automation that compiles down to Actions YAML but lets AI agents make runtime decisions. It walks you through the full lifecycle: authoring workflows with proper frontmatter and safe outputs, setting up Copilot authentication, running gh aw compile and trial commands, and debugging common pitfalls like concurrency groups in matrix jobs or secret scope issues. The procedures are opinionated and specific, like preferring safe outputs over direct write permissions and warning you that runtime placeholders don't reach the agent body the way you'd expect. Use this when you're building or maintaining GH-AW automation, not standard deterministic Actions.

skills.sh installs: 486
GitHub stars: 1
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add webmaxru/ai-native-dev --skill github-agentic-workflows --agent claude-code

Installs into .claude/skills of the current project.

Files

GitHub Agentic Workflows

Procedures

Step 1: Identify the repository state

Inspect the workspace for .github/workflows/, .github/agents/, existing .lock.yml files, and any gh aw usage.
Execute node skills/github-agentic-workflows/scripts/find-gh-aw-targets.mjs . when a Node runtime is available.
Run gh aw version before making compiler-sensitive decisions so the workflow authoring path matches the installed CLI behavior.
If the repository contains multiple candidate workflows, prefer the workflow the user named or the one closest to the active issue, pull request, or automation surface.
If the repository has no GH-AW setup and the task is to create or maintain agentic workflows, read references/authoring.md before editing.
If the task is limited to standard deterministic GitHub Actions YAML without agentic markdown workflows, stop and explain that this skill does not apply.