Skip to content

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

creating-skills

Verified

Creates GitHub Copilot skills with reusable workflows, companion resources, and validation gates. Use when packaging repeatable expertise into a `SKILL.md` folder, deciding what belongs in the skill body versus resources, or producing install-ready skill examples for a team or collection.

FileKindSize
SKILL.mdskill md5.2 KB
resources/SKILL.example.mdmarkdown1.9 KB
resources/SKILL.template.mdmarkdown1.5 KB
resources/skill-quality-checklist.mdmarkdown1.7 KB

resources/SKILL.template.md

View on GitHub
---
name: <activity-name>
description: '<What this skill does>. Use when <trigger contexts and user intents>.'
argument-hint: '<What the user should provide>'
user-invocable: true
---

# <Human friendly skill title>

Use this skill when <the task deserves a reusable workflow instead of ad-hoc guidance>.
It should help the agent move from input to output with minimal guesswork.

## When to Use

Use this skill when the user asks for things like:

- "<example request>"
- "<example request>"
- "<example request>"

Typical scenarios:

- <scenario>
- <scenario>
- <scenario>

## Outcome Standard

A strong result usually includes:

- <deliverable>
- <deliverable>
- <validation or decision aid>

## Workflow

### Phase 0: Frame the task

- confirm scope, inputs, and expected outputs
- identify missing context that must be clarified or discovered

### Phase 1: Gather the right context

- inspect the repository, docs, or files that matter
- collect only the information needed to do the job well

### Phase 2: Produce the outcome

- follow the default approach for this skill
- create the main artifact or analysis
- reference supporting resources when needed

### Phase 3: Validate

- verify the result against quality gates or acceptance criteria
- summarize any unresolved risks or follow-ups

## Resource Map

- `./resources/<template-or-checklist>.md` - <why it matters>
- `./resources/<example>.md` - <why it matters>

## Definition of Done

A task using this skill is complete when:

- <completion criterion>
- <completion criterion>
- <completion criterion>
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