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.example.md

View on GitHub
---
name: analyzing-test-reports
description: 'Analyzes CI test reports to identify dominant failure themes, flakiness signals, and the next investigation steps. Use when triaging failed builds, recurring flaky suites, or release-candidate test instability.'
argument-hint: 'Test report summary, failed jobs, and the scope to analyze'
user-invocable: true
---

# Analyzing Test Reports

Use this skill when a build fails and the important problem is buried under noise.
It helps turn a pile of red results into a prioritized investigation summary.

## When to Use

Use this skill when the user asks for things like:

- "analyze this failed CI run"
- "group the failures and tell me what matters first"
- "is this build flaky or genuinely broken?"

Typical scenarios:

- nightly regression failures
- repeated retry-only pipelines
- release candidate verification

## Outcome Standard

A strong result usually includes:

- the dominant failure clusters
- the likeliest root-cause candidates
- the next best debugging steps

## Workflow

### Phase 0: Frame the failure set

- identify the failing suites, environments, and time window
- separate new failures from recurring noise

### Phase 1: Group the signals

- cluster failures by symptom, stack trace, test target, or infrastructure dependency
- note where the same fault appears under multiple test names

### Phase 2: Assess confidence

- label findings as likely product bug, test bug, infrastructure issue, or unknown
- call out where evidence is weak and further logs are required

### Phase 3: Recommend next actions

- prioritize the smallest set of checks that can confirm or disprove the leading theory
- separate urgent containment from longer-term stability work

## Definition of Done

A task using this skill is complete when:

- the key failure groups are clear
- the likely causes are ranked by confidence
- the next debugging actions are actionable and ordered
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: 471kUpdated 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