Skip to content

jaktestowac/awesome-copilot-for-testers / plugins/creating-custom-agents/skills/creating-custom-agents

creating-custom-agents

Verified

Creates GitHub Copilot custom agents (`.agent.md`) for VS Code. Use when defining a specialized agent role, selecting a minimal toolset, referencing supporting skills, or shipping install-ready agent examples with clear boundaries and collaboration rules.

resources/custom-agent-quality-checklist.md

View on GitHub
# Custom Agent Quality Checklist

Use this checklist before finalizing a GitHub Copilot custom agent.

## Role clarity

- [ ] The agent has a clearly bounded mission.
- [ ] The description makes it obvious when the agent should be used.
- [ ] The file defines identity and responsibilities, not a huge procedural manual.

## Tools and model

- [ ] The selected tools are minimal and intentional.
- [ ] Any powerful tool access is justified by the role.
- [ ] The model choice is deliberate when a model is specified.

## Separation of concerns

- [ ] Detailed reusable workflows are delegated to skills when appropriate.
- [ ] One-off entrypoints are delegated to prompt files when appropriate.
- [ ] Repository-wide coding rules are not duplicated from instruction files.

## Behavior quality

- [ ] The default workflow is short, useful, and realistic.
- [ ] Constraints or anti-patterns are explicit.
- [ ] Output expectations are concrete enough to shape responses.

## Final handoff

- [ ] The file is install-ready and internally consistent.
- [ ] The agent is distinct from nearby agents.
- [ ] A template or example exists when the artifact is meant for reuse.

## Smells that should trigger a rewrite

- "does everything" scope
- giant tool arrays added as a shortcut
- copied skill content inside the agent body
- no explanation of when the agent should be chosen
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall