GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension for writing Agentic Workflows in markdown and compiling them to GitHub Actions.
github/gh-aw
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 107
- GitHub stars
- 5,624
- GitHub forks
- 625
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/github/gh-aw.Loading the repository README…
Skills in this repository
Showing 40 of 107 collected skills.
Route gh-aw design, creation, diagnosis, patching, active debugging, upgrades, and local SDLC issue requests to the right strategies.
Troubleshoot npm registry, proxy, and certificate failures on the Microsoft corporate network or VPN using the 1ES public npm feed.
Create or extend a declaration-only third-party connector, with narrow reads, separate safe outputs, optional protected triggers, and offline conformance evidence.
{what this skill teaches agents}
PAO workflow for scanning, drafting, and presenting community responses with human review gate
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
Core developer rules and coding conventions for gh-aw changes.
The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for…
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode. This skill contains the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the…
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand…
Detect and set up account-locked gh aliases for multi-account GitHub. The AI reads this skill, detects accounts, asks the user which is personal/work, and runs the setup automatically.
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable
Internals of how @bradygaster/squad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.
Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
Build and refactor issue, comment, and review bodies in actions/setup/js using typed report trees and a single publication render.
Internal gh-aw architecture: validation, pure session graders, safe output messages, schema validation, YAML compatibility, and MCP logs guardrail.
Design recorded-session outcome metrics using built-ins, isolated JavaScript, or separate-job operational-value Bash. Usage: /operational-value-designer OWNER/REPO WORKFLOW-NAME.
Diagnose gh-aw failures using the canonical debugging strategy and evidence reference.
Review agentic workflow changes for correctness, security posture, and optimization opportunities with compile, validation, and audit evidence.
Implement and test Go codemods for the gh aw fix command.
Operate safely and efficiently inside a gh-aw workflow with a restricted tools/bash allowlist, and correctly triage tool-denial events before they exhaust the session's denial budget.
Generate an eight-panel repository statistics infographic with individual-PR diff histograms and human/agent comment and commit comparisons.
Security best practices for gh-aw workflows and Go code: template injection prevention, shell script security, supply chain hardening, and static analysis integration.
Maintain model-routing audit golden fixtures and expected outputs.
Prepare an open pull request for merge from a GitHub Copilot cloud agent. Drives Reviews, local validation, and Mergeable to a ready state. Does not merge, and cannot trigger CI.
Design rules for the docs site and landing page (docs/). Use before any visual change there — layout, widths, spacing, colour, typography, header navigation, or new page chrome.
Add and validate custom Go analysis linters in gh-aw.
Split large JavaScript files into maintainable modules safely.
Add new safe-output message types and wire validation/rendering.
Analyze gh-aw OpenTelemetry traces from JSONL mirrors or OTLP backends.
Add and test declarative behavior-defined agentic engines in gh-aw, extending Go infrastructure only when necessary.
Teach Copilot how to plan, address, and respond to pull request review feedback.
Merge a base ref and safely regenerate compiled workflow lock-file conflicts.
Apply safe error-pattern matching rules for agentic engines.
Add temporary ID support to safe-output jobs end to end.
Query GitHub discussions with jq filtering and reusable selectors.
Review a GitHub security advisory and safely update .github/aw/compat.json with evidence-backed version enforcement.
Upgrade gh-aw to latest gh-aw-firewall release and identify follow-up spec tasks.
Publish validated gh-aw changes as a draft pull request from a cloud agent.