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
SkillsMP has collected 48 skills from github/gh-aw. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 48
- GitHub stars
- 4,937
- GitHub forks
- 497
Skills in this repository
Showing 40 of 48 collected skills.
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.
Optional Sergo examples for cache formats and reporting templates.
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
Add and validate custom Go analysis linters in gh-aw.
Review code that performs git or gh operations against repository checkouts in gh-aw, checking that the right credentials are available at the right time and that sparseness, shallowness and credential-free factors are properly considered.
Debug gh-aw workflows using run logs, audits, and failure triage.
Internal gh-aw architecture: validation system design, safe output message patterns, schema validation, YAML compatibility notes, and MCP logs guardrail.
Security best practices for gh-aw workflows and Go code: template injection prevention, shell script security, supply chain hardening, and static analysis integration.
Design gh-aw error handling, retry, recovery, and debugging flows.
Implement secret-safe HTTP headers for MCP transport in gh-aw.
Run and integrate Skillz MCP server with Docker for skill execution.
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.
List GitHub repository labels with per_page pagination and name filtering support.
Core developer rules and coding conventions for gh-aw changes.
Reference for GitHub MCP server tools, methods, and usage patterns.
Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.
Release management, changeset workflow, firewall log parsing, breaking CLI change rules, and Go module summaries for gh-aw.
Merge a base ref and safely regenerate compiled workflow lock-file conflicts.
List GitHub Actions workflows with per_page pagination support.
Teach Copilot how to plan, address, and respond to pull request review feedback.
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.
Define and validate GitHub custom agent files, prompts, and examples.
Author, validate, and debug canvas extensions that the agent can open in the GitHub Copilot app's side panel. Use when creating, reviewing, or troubleshooting a canvas extension — including its actions, inputs, rendered content, and the surrounding extension…
Infer JSON structure and types with jq-based schema discovery.
Query GitHub pull requests with jq filtering and reusable selectors.
Rewrite prompts for minimal tokens, maximal clarity, and low ambiguity for LLM consumption.
Write clear GitHub Actions step summaries with progressive disclosure.
Implement and test Go codemods for the gh aw fix command.
Automate browser interactions, test web pages and work with Playwright tests.
Write consistent, actionable validation error messages in gh-aw.
Format reports with HTML details/summary blocks for readable output.
Normalize SKILL.md artifacts into Scheduling-Structural-Logical (SSL) JSON representations using a conservative multi-pass extraction pipeline.
Generate a new pkg/linters analyzer from a merged or open PR pattern.
Upgrade gh-aw to latest gh-aw-firewall release and identify follow-up spec tasks.
Use Go struct tags to render styled terminal output in gh-aw.
Write concise Diataxis docs for gh-aw with Starlight markdown conventions.
Apply safe error-pattern matching rules for agentic engines.
Use gh agent-session commands to inspect and manage agent sessions.
Use gh agent-task commands to create, run, and monitor agent tasks.