By aks-builds
Quality engineering skills for QA engineers, SDETs, and test automation leads — covering frontend (Selenium/Cypress/Playwright), API (Postman/REST Assured/Karate), performance (k6/JMeter/Gatling), mobile (Appium), BDD, accessibility, visual regression, security, chaos, contract testing, CI orchestration, and quality strategy
When the user wants to design, implement, or operate accessibility (a11y) testing — automated scans, manual audits, screen-reader testing, WCAG conformance, Section 508 / EAA compliance. Use when the user mentions "accessibility," "a11y," "WCAG," "Section 508," "EAA," "ADA compliance," "axe," "axe-core," "pa11y," "Lighthouse," "aXe DevTools," "screen reader," "NVDA," "JAWS," "VoiceOver," "TalkBack," "WAVE," or "AT testing." For visual diff see visual-regression. For overall test strategy see test-strategy.
When the user wants to evaluate, adopt, or operate AI-augmented testing tools and approaches — autonomous test generation, self-healing locators, AI-assisted authoring, vision-based testing, agentic test runners. Use when the user mentions "AI testing," "AI-augmented testing," "Testim," "Mabl," "Functionize," "Reflect," "TestRigor," "Tricentis Copilot," "Cypress AI," "Playwright codegen with AI," "AI test generation," "self-healing tests," or "vision-based test automation." For LLM-product evals see llm-eval-testing. For overall strategy see test-strategy.
When the user wants to design, implement, debug, or scale Appium tests for iOS and Android mobile automation. Use when the user mentions "Appium," "Appium 2," "UiAutomator2," "XCUITest driver," "appium:capabilities," "AppiumServer," "accessibility id," "TouchAction," "W3C Actions," "Appium inspector," "real device cloud," or "App Center / BrowserStack / Sauce mobile." For Android-native frameworks see espresso. For iOS-native see xcuitest. For React Native specifically see detox. For YAML-driven mobile flows see maestro. For desktop web automation see selenium / playwright / webdriverio.
When the user wants to design, implement, debug, or operate Artillery load tests. Use when the user mentions "Artillery," "artillery.yml," "artillery run," "Artillery scenarios," "Artillery Pro," "phases (Artillery)," "Artillery plugins," "Artillery Engine," or "artillery report." For JS-tested perf with thresholds see k6. For JVM perf see gatling. For Python see locust. For JMeter see jmeter.
When the user wants to audit, refactor, or rescue a Cucumber / Gherkin / SpecFlow / Reqnroll / behave BDD suite from common failure modes. Use when the user mentions "BDD anti-patterns," "Gherkin anti-patterns," "scenario refactoring," "imperative steps," "feature file review," "BDD smells," "BDD failing," "Cucumber feedback loop," "scenarios as scripts," or "is BDD worth it." For Cucumber/Gherkin basics see cucumber-gherkin. For .NET BDD see specflow-reqnroll. For Python BDD see behave.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Give your AI agent the QA instincts of a senior SDET.
106 production-grade skills covering the complete quality engineering ecosystem — frontend automation, API testing, performance, mobile, BDD, accessibility, security, chaos engineering, contract testing, CI orchestration, and quality strategy. Works with Claude Code, Claude Desktop, Cursor, Zed, Windsurf, and any agent that speaks MCP or the Agent Skills spec.
☝️ Claude Code invoking the playwright_scaffold tool — one of 260+ typed MCP tools in this collection.
AI coding agents are great at writing code — but without domain knowledge, they fabricate CLI flags, invent config keys, and generate test patterns that look right but break in CI. quality-skills gives your agent accurate, up-to-date knowledge of 40+ test automation tools and frameworks, so it helps you write tests that actually pass.
Every skill reads your project's qa-context first — your stack, languages,
CI provider, browsers in scope — then applies the right tool idioms, not generic
advice. The result: an agent that knows the difference between page.locator
and page.find, understands k6 thresholds, and won't suggest Selenium when
you're already on Playwright.
It works as a Claude Code plugin (one command to install), an MCP server
(any MCP-compatible agent — Claude Desktop, Cursor, Zed, Windsurf, custom
agents), or a plain file copy into .agents/skills/.
Skills reference each other and build on shared context. qa-context is the
foundation — every other skill reads it first to understand your stack before
doing anything.
┌───────────────────────────────┐
│ qa-context │
│ (read by all skills first) │
└───────────────┬───────────────┘
│
┌──────────┬───────────┬─────────────┼─────────────┬───────────┬──────────┐
▼ ▼ ▼ ▼ ▼ ▼ ▼
Strategy Frontend API Performance Mobile A11y & CI &
Automation Testing & Load Testing Visual Infra
See each skill's Related Skills section for the full dependency map.
/plugin marketplace add aks-builds/quality-skills
/plugin install quality-skills
Add to your mcp_servers config (e.g. .mcp.json or claude_desktop_config.json):
{
"mcpServers": {
"quality-skills": {
"command": "npx",
"args": ["github:aks-builds/quality-skills/mcp"]
}
}
}
Or if you have it cloned locally:
{
"mcpServers": {
"quality-skills": {
"command": "node",
"args": ["/path/to/quality-skills/mcp/index.js"]
}
}
}
git clone https://github.com/aks-builds/quality-skills.git
cp -r quality-skills/skills/* .agents/skills/
git submodule add https://github.com/aks-builds/quality-skills.git .agents/quality-skills
Once installed, ask your agent naturally:
"Set up Playwright for our Next.js app with parallel execution and tracing"
→ playwright_scaffold + ci-test-orchestration
"Why are these Cypress tests flaky?"
→ cypress + flaky-test-management
"Build a k6 load test for our checkout API targeting 200 RPS"
→ k6_scaffold + qa-context
"Add Pact contract testing between our web app and orders API"
→ pact-contract-testing + rest-assured
"Write a Cucumber feature for the password reset flow"
→ cucumber-gherkin + bdd-anti-patterns
Or invoke skills directly:
/playwright
/k6
/accessibility-testing
/hipaa-compliance
npx claudepluginhub aks-builds/quality-skills --plugin quality-skillsProve your CLI actually works. Captures a real terminal command and its real output as a polished screenshot (or GIF) and embeds it into your README as proof-it-runs evidence.
Read your service code and generate ready-to-import API test collections for every tool (Postman, OpenAPI, Insomnia, Bruno, Hoppscotch, Thunder Client, .http) with exhaustive request variants per endpoint.
Root cause in seconds. Evidence, not intuition. Analyzes Playwright, Jest, Cypress, Newman, k6, and JUnit test failures by tracing real evidence from git, logs, and config — no guesses, no fixture noise.
41 healthcare skills for engineers, informaticists, and product builders covering EHR integration, FHIR/HL7 interoperability, HIPAA compliance, clinical AI/ML, telehealth, revenue cycle, and more
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.