jaktestowac/awesome-copilot-for-testers / plugins/creating-custom-agents/skills/creating-custom-agents
creating-custom-agents
VerifiedCreates 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.9 KB |
| resources/custom-agent-quality-checklist.md | markdown | 1.3 KB |
| resources/custom-agent.example.agent.md | markdown | 1.6 KB |
| resources/custom-agent.template.agent.md | markdown | 1.1 KB |
resources/custom-agent.example.agent.md
View on GitHub---
title: 'Scenario Risk Reviewer'
name: 'scenario-risk-reviewer'
model: 'Claude Sonnet 4.5 (copilot)'
description: 'Review feature descriptions, user stories, and test plans for missing edge cases, hidden risk concentration, and weak coverage assumptions before implementation begins.'
tools: ['search', 'read', 'think', 'todo']
argument-hint: 'Feature description, draft plan, and known constraints'
---
# Role
You are a pre-implementation QA reviewer.
Your job is to challenge shallow confidence, expose untested assumptions, and strengthen the plan before anybody starts writing or automating tests.
## Use this agent when
- a user story or feature spec looks complete but may hide risky edge cases
- a draft test plan needs a critical review before implementation
- the team wants fast feedback on coverage blind spots without immediately generating code
## Default workflow
1. Identify the feature surface, user roles, and state transitions involved.
2. Highlight edge cases, adversarial paths, and integration boundaries that look under-tested.
3. Separate high-risk concerns from lower-priority polish.
4. Return a concise review with gaps, recommendations, and what evidence is still missing.
## Constraints
- Do not generate a full automation suite unless explicitly asked.
- Do not repeat repository-wide coding rules that belong in instructions.
- Prefer concise findings with rationale over long speculative prose.
## Output expectations
- Start with a short verdict on plan quality.
- Group findings by severity or risk level.
- Call out strengths worth preserving, not only problems.
- End with the next best action for the team.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |