Skill Finder
The best Claude skills for testing and TDD
Start with tdd from Matt Pocock: among skills made for testing it has the top score, 87, plus over 1.1 million installs and no extra needs, and it makes Claude build features one failing test at a time. Next comes webapp-testing from Anthropic, which checks web apps on your own machine with Playwright. The list also covers next-dev-loop, golang-testing, vitest and simulator setup.
The 8 skills made for this job
-
1
Get tddtdd
For developers who want Claude to build features test first, one failing test at a time. Skip it if you want a whole test suite written in one go.
-
2
Get webapp-testingwebapp-testing
For developers who want Claude to click through a web app running on their own machine and see what breaks. Skip it if the site is only live on a remote server.
-
3
Get next-dev-loopnext-dev-loop
For Next.js developers on Turbopack who want each edit confirmed in a real browser. Skip it if you're below Next.js 16.3, on webpack, or not running next dev.
-
4
Get argent-ios-simulator-setupargent-ios-simulator-setup
For Argent users who need an iOS simulator booted and connected before Claude taps through an app. Skip it if you test on Android only or do not have Argent's MCP tools.
-
5
Get argent-android-emulator-setupargent-android-emulator-setup
For mobile developers using Argent who need Claude to boot and connect to an Android emulator. Skip it if you test on iOS only or don't use Argent's MCP tools.
-
6
Get playwright-best-practicesplaywright-best-practices
For teams writing Playwright end-to-end, component or API tests who want a guide picked for each task. Skip it if your tests use another runner.
-
7
Get golang-testinggolang-testing
For Go developers writing, reviewing or debugging tests, from table-driven cases to fuzzing and leak checks. Skip it if your code is not in Go or you only need testify API details.
-
8
Get vitestvitest
For JavaScript and TypeScript developers writing or fixing Vitest tests and config. Skip it if your project runs Jest, Mocha or another runner and you are not moving to Vitest.
Also useful for testing
Their main job is something else, but they help with this one.
-
Get Google Agents CLIGoogle Agents CLI
For developers building AI agents with Google's ADK who want guidance from scaffold to deploy. Skip it if your agents will not run on Google Cloud.
-
Get agent-browseragent-browser
For developers who want Claude to drive Chrome from the terminal to click, fill forms and take screenshots. Skip it if you cannot install a global npm tool.
-
Get browser-usebrowser-use
For developers who want Claude to drive their own Chrome, or a hosted cloud browser, through the DevTools protocol. Skip it if a plain fetch can read the page.
-
Get systematic-debuggingsystematic-debugging
For developers whose AI keeps guessing at fixes and who want the root cause found first. Skip it if you just need a typo or one-line slip corrected.
-
Get writing-planswriting-plans
For developers who give Claude a spec and want a test-first build plan before any code is written. Skip it for small fixes you could make in one step.
-
Get solana-devsolana-dev
For developers building Solana programs, clients or wallet UIs who want current tooling defaults. Skip it if you are not working on Solana.
-
Get expo-dev-clientexpo-dev-client
For Expo app developers who need a custom development build on a phone or in TestFlight. Skip it if Expo Go runs your app or you are shipping a store release.
-
Get argent-react-native-optimizationargent-react-native-optimization
For React Native developers chasing slow screens, jank or extra re-renders who want measurement before changes. Skip it if you do not use the Argent toolkit or your app is not React Native.
-
Get angular-developerangular-developer
For Angular developers who want Claude to write version-aware, current Angular code and check it builds. Skip it if you work in React, Vue or another framework.
-
Get neon-postgres-branchesneon-postgres-branches
For teams on Neon Postgres who want to test migrations on a copy of production. Skip it if your database isn't on Neon or you never branch data for tests.
-
Get agent-deviceagent-device
For mobile and TV app developers who want Claude to tap through apps on simulators and devices. Skip it if you only test web pages in a browser or cannot install the agent-device CLI.
-
Get Claude Code Game StudiosClaude Code Game Studios
For solo or small-team game developers who want a staged studio process from concept to release. Skip it if you just want help with one script in your engine.
-
Get penetration-testing-with-strixpenetration-testing-with-strix
For developers who want automated pentests that prove each finding with a working exploit. Skip it if you can't confirm you are authorized to attack the target.
-
Get opentuiopentui
For developers building terminal apps with OpenTUI's Core, React or Solid API. Skip it if your terminal UI uses another library or you can't run Bun.
How to choose
tdd fits when you want features built test first. Claude lists the public interfaces to test at and gets your agreement, then writes one failing test and just enough code to pass it. It needs nothing beyond Claude Code. Skip it if you want a whole suite written at once.
webapp-testing has Claude write Python Playwright scripts against a web app on your machine. A bundled helper can start the backend and frontend, and Claude takes a screenshot or reads the DOM before it clicks or types. It needs Python with Playwright and Chromium.
Pick a guide for your stack. golang-testing writes, reviews and audits Go tests and needs the gotests tool. vitest is a reference map of the Vitest runner. playwright-best-practices routes Claude to Playwright guides and reruns key tests; at least one scanner rated it high risk.
next-dev-loop checks each Next.js edit in the running app. It needs next dev on Next.js 16.3 or later with Turbopack, plus agent-browser 0.31.1 or newer. For mobile apps, argent-ios-simulator-setup and argent-android-emulator-setup get a simulator or emulator ready for the Argent MCP tools.
The rest are secondary picks from other jobs. systematic-debugging ends each fix with a failing test, and writing-plans turns a spec into test-first tasks. Claude Code Game Studios includes playtest reports and balance checks. penetration-testing-with-strix runs automated pentests; it and agent-browser carry high-risk scanner results.