playwright-cli
github/gh-aw/.claude/skills/playwright-cli/SKILL.md
Automate browser interactions, test web pages and work with Playwright tests.
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
github/gh-aw/.claude/skills/playwright-cli/SKILL.md
Automate browser interactions, test web pages and work with Playwright tests.
github/gh-aw/docs/src/content/docs/engines/claude.md
Select and authenticate Claude Code as the AI engine for GitHub Agentic Workflows, understand its capabilities and limitations, and start from an example.
github/gh-aw/.github/skills/awf-release-integrator/SKILL.md
Upgrade gh-aw to latest gh-aw-firewall release and identify follow-up spec tasks.
github/gh-aw/.github/skills/checkout-credential-review/SKILL.md
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.
github/gh-aw/.github/skills/console-rendering/SKILL.md
Use Go struct tags to render styled terminal output in gh-aw.
github/gh-aw/.github/skills/copilot-review/SKILL.md
Teach Copilot how to plan, address, and respond to pull request review feedback.
github/gh-aw/.github/skills/create-canvas/SKILL.md
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 wiring (tools, hooks, lifecycle).
github/gh-aw/.github/skills/custom-agents/SKILL.md
Define and validate GitHub custom agent files, prompts, and examples.
github/gh-aw/.github/skills/custom-engine-implementation/SKILL.md
Add and test declarative behavior-defined agentic engines in gh-aw, extending Go infrastructure only when necessary.
github/gh-aw/.github/skills/debugging-workflows/SKILL.md
Debug gh-aw workflows using run logs, audits, and failure triage.
github/gh-aw/.github/skills/developer-code-organization/SKILL.md
Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.
github/gh-aw/.github/skills/developer-internals/SKILL.md
Internal gh-aw architecture: validation system design, safe output message patterns, schema validation, YAML compatibility notes, and MCP logs guardrail.
github/gh-aw/.github/skills/developer-release/SKILL.md
Release management, changeset workflow, firewall log parsing, breaking CLI change rules, and Go module summaries for gh-aw.
github/gh-aw/.github/skills/developer-security/SKILL.md
Security best practices for gh-aw workflows and Go code: template injection prevention, shell script security, supply chain hardening, and static analysis integration.
github/gh-aw/.github/skills/developer/SKILL.md
Core developer rules and coding conventions for gh-aw changes.
github/gh-aw/.github/skills/documentation/SKILL.md
Write concise Diataxis docs for gh-aw with Starlight markdown conventions.
github/gh-aw/.github/skills/error-messages/SKILL.md
Write consistent, actionable validation error messages in gh-aw.
github/gh-aw/.github/skills/error-pattern-safety/SKILL.md
Apply safe error-pattern matching rules for agentic engines.
github/gh-aw/.github/skills/error-recovery-patterns/SKILL.md
Design gh-aw error handling, retry, recovery, and debugging flows.
github/gh-aw/.github/skills/gh-agent-session/SKILL.md
Use gh agent-session commands to inspect and manage agent sessions.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.