Skip to content

jaktestowac/awesome-copilot-for-testers / plugins/creating-prompts/skills/creating-prompts

creating-prompts

Verified

Creates GitHub Copilot prompt files (`.prompt.md`) for VS Code. Use when building reusable workflow starters that route work to the right agent, collect the right inputs, and ship with install-ready templates, examples, and validation guidance.

resources/prompt.example.prompt.md

View on GitHub
---
name: 'Review Test Plan Gaps'
agent: 'test-planner'
description: 'Review a draft test plan for missing risks, low-value scenarios, and untested integration edges before implementation begins.'
model: 'Claude Sonnet 4.5 (copilot)'
argument-hint: 'Draft plan, feature summary, and known constraints'
---

Review the provided draft test plan and strengthen it before implementation starts.
If required inputs are missing, ask only for the smallest missing set before proceeding.

## Inputs

- Draft test plan: `${input:draftPlan:Paste the plan or point to a file}`
- Feature summary: `${input:featureSummary:Describe the feature or user journey}`
- Optional constraints: `${input:constraints:Environment, deadlines, or out-of-scope areas}`

## Workflow

1. Read the draft plan and identify the intended coverage, assumptions, and priorities.
2. Highlight missing edge cases, security concerns, integration blind spots, and low-signal scenarios.
3. Recommend the smallest high-impact improvements before any automated test work begins.
4. Summarize the revised priorities and the next best action for the team.

## Output expectations

- a short verdict on the draft plan quality
- a grouped list of coverage gaps and improvement recommendations
- a concise next-step recommendation

## Constraints

- Stay in review mode unless the user explicitly asks for a rewritten plan.
- Focus on risk and coverage, not formatting polish.
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