e2e-template-testing
github/gh-aw/.squad/templates/skills/e2e-template-testing/SKILL.md
End-to-end validation of coordinator and agent template changes
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.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
github/gh-aw/.squad/templates/skills/e2e-template-testing/SKILL.md
End-to-end validation of coordinator and agent template changes
github/gh-aw/.squad/templates/skills/economy-mode/SKILL.md
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
github/gh-aw/.squad/templates/skills/error-recovery/SKILL.md
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
github/gh-aw/.squad/templates/skills/external-comms/SKILL.md
PAO workflow for scanning, drafting, and presenting community responses with human review gate
github/gh-aw/.squad/templates/skills/fact-checking/SKILL.md
Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.
github/gh-aw/.squad/templates/skills/gh-auth-isolation/SKILL.md
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
github/gh-aw/.squad/templates/skills/github-multi-account/SKILL.md
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.
github/gh-aw/.squad/templates/skills/git-workflow/SKILL.md
Squad branching model: dev-first workflow with insiders preview channel
Often used withsquad-commandsci-cd-pipelines
github/gh-aw/.squad/templates/skills/history-hygiene/SKILL.md
Record final outcomes to history.md, not intermediate requests or reversed decisions
github/gh-aw/.squad/templates/skills/humanizer/SKILL.md
Tone enforcement patterns for external-facing community responses
github/gh-aw/.squad/templates/skills/init-mode/SKILL.md
Team initialization flow (Phase 1 proposal + Phase 2 creation)
github/gh-aw/.squad/templates/skills/iterative-retrieval/SKILL.md
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
Often used withproject-guidelines-exampleconfigure-eccralphinho-rfc-pipeline
github/gh-aw/.squad/templates/skills/model-selection/SKILL.md
Determines which LLM model to use for each agent spawn
github/gh-aw/.squad/templates/skills/nap/SKILL.md
Context hygiene — compress, prune, archive .squad/ state
github/gh-aw/.squad/templates/skills/notification-routing/SKILL.md
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
github/gh-aw/.squad/templates/skills/personal-squad/SKILL.md
User-level AI agents that travel with you across projects
github/gh-aw/.squad/templates/skills/project-conventions/SKILL.md
Core conventions and patterns for this codebase
github/gh-aw/.squad/templates/skills/pr-review-response/SKILL.md
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable
github/gh-aw/.squad/templates/skills/pr-screenshots/SKILL.md
Capture Playwright screenshots and embed them in GitHub PR descriptions
github/gh-aw/.squad/templates/skills/ralph-two-pass-scan/SKILL.md
Cuts GitHub API calls by separating lightweight list scanning from full hydration
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.