🤖

AI EngineeringGo

Custom Agents

Custom Agents is an AI Engineering skill for Claude Code, published by github in gh-aw.

4.9K stars495 forkson github/gh-awAdded 2026/08/16Repository updated 2026/08/16

View source on GitHub Download repo ZIP

actionscaiciclaude-codecodexcopilotgh-extensiongithub-actions

Install in seconds

Install Custom Agents

Copy Custom Agents into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/github/gh-aw/tree/main/.github/skills/custom-agents ~/.claude/skills/custom-agents

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/github/gh-aw.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .github/skills/custom-agents/SKILL.md in github/gh-aw
Installs to: ~/.claude/skills/custom-agents
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Custom Agents does

Custom Agents defines and validates GitHub custom agent files, prompts, and examples. Use it to create agent profiles, path-specific instructions, and workflow-specific agent configurations.

Custom Agents is cataloged under AI Engineering on DirSkills. Custom Agents comes from a repository tagged actions, cai, ci, claude-code and codex.

Documentation

README

Excerpt

GitHub Custom Agent File Format

Use this reference for the GitHub custom agent file format.

Overview

GitHub Copilot reads custom agent instructions from Markdown files with YAML frontmatter. Use them to define specialized behavior, tool access, and workflows for your repository.

File Locations

Place custom agent files in these locations based on scope:

1. Repository-wide Instructions

File: .github/copilot-instructions.md
Scope: Applies to all code generation in the repository
Use case: General coding standards, security requirements, testing practices

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Custom Agents

What else does github publish alongside Custom Agents?
Custom Agents is one of 25 skills that DirSkills catalogs from github/gh-aw, the repository it ships in. Its siblings there include AWF Release Integrator, Agent Session CLI and Agent Task CLI. Each one is a separate skill with its own page in this directory, installs the same way Custom Agents does, and is maintained by github in that same repository. The rest of the collection is listed on the github/gh-aw page.
How does Custom Agents compare to other AI Engineering skills?
Custom Agents ranks #514 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Custom Agents against them. Open each page to compare what they document and how they install.

More from github/gh-aw

Custom Agents is one of 25 skills cataloged on DirSkills from github/gh-aw.

See all 25 skills →

AWF Release Integrator

AWF Release Integrator upgrades gh-aw to the latest gh-aw-firewall release, bumps version constants, rebuilds generated artifacts, and reviews upstream spec changes to identify follow-up tasks.

Agent Session CLI

Agent Session CLI uses the gh agent-session command to inspect and manage GitHub Copilot coding agent sessions, including creating tasks from natural language instructions, listing, viewing, and updating them.

Agent Task CLI

Agent Task CLI creates GitHub Copilot coding agent tasks from the command line, using natural language instructions that trigger automated code changes and pull requests. Use it to delegate coding work, list and view tasks, and integrate with GitHub Agentic Workflows.

Agentic Workflows

Agentic Workflows compiles Markdown-defined AI agent jobs into GitHub Actions, so developers can define AI-powered repository automation and run AI agents securely through GitHub Actions for reasoning tasks.

Agentic Workflows Router

Agentic Workflows Router dispatches user requests to design, create, update, debug, or upgrade GitHub Agentic Workflows to the correct internal prompt or skill file. Use it when working on agentic workflows in a repository, and follow the matched instructions directly.

Checkout Credential Review

Checkout Credential Review helps review code that performs git or gh operations against repository checkouts, ensuring the right credentials are available at the right time and that sparseness, shallowness, and credential-free factors are considered.

More AI Engineering skills

Custom Agents is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #514 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.