Category · Testing & Review

Testing & Review skills for Claude Code

The best Testing & Review skills, MCP servers & marketplaces for Claude Code, Codex, Cursor & all other coding agents, ranked by real installs in the Testing & Review category. Covers Jest, Playwright, Vitest and pytest and more.

What's in the Testing & Review category

The Testing & Review category collects 3,971 tools including agent skills, marketplaces and plugins, led by Improve Codebase Architecture, Tdd and Codebase Design. The list is updated automatically and ranked by real adoption - installs first, then GitHub stars - so the strongest surface first. Every listing works with Claude Code, Codex or Cursor. Updated September 10, 2026.

Use the filters below to narrow by type or what you're building, or open a type hub to see testing & review listings alongside everything else of that type.

Browse tools

Showing 718 of 3,971 in this view.

Type

1Improve Codebase Architecturemattpocock/skillsSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.Testing & Reviewskill

881k253k

2Tddmattpocock/skillsFollow test-driven development with a strict red-green-refactor loop when creating reliable features or fixing bugs.Testing & Reviewskill

853k253k

3Codebase Designmattpocock/skillsShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.Testing & Reviewskill

564k253k

4Code Reviewmattpocock/skillsReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.Testing & Reviewskill

500k253k

5Caveman ReviewJuliusBrussee/cavemanGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.Testing & Reviewskill

338k104k

6Analyze Projectlllllllama/RigorPilot-SkillsGet a conservative, read-only map of any deep-learning repository before deciding where to safely insert new agent logic.Testing & Reviewskill

311k484

7Migrate To Shoehornmattpocock/skillsAutomatically update TypeScript test files that rely on unsafe `as` type assertions by replacing them with type-safe partial objects from @total-typescript/shoehorn.Testing & Reviewskill

308k253k

8CavecrewJuliusBrussee/cavemanDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.Testing & Reviewskill

287k104k

9Requesting Code Reviewobra/superpowersDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.Testing & Reviewskill

221k282k

10Test Driven Developmentobra/superpowersEnforce writing failing tests before any production implementation code.Testing & Reviewskill

219k282k

11Verification Before Completionobra/superpowersEnforce evidence-based completion claims and eliminate unverified assertions before commits or PRs.Testing & Reviewskill

202k282k

12Setup Ts Deep Modulesmattpocock/skillsInstall dependency-cruiser and enforce deep-module boundaries in a TypeScript monorepo so packages expose only root entry points.Testing & Reviewskill

199k253k

13Receiving Code Reviewobra/superpowersRespond to code review feedback with technical rigor instead of performative agreement.Testing & Reviewskill

186k282k

14Google Agents Cli Evalgoogle/agents-cliOfficialAccurately evaluate agent trajectories that rely on Google Search grounding instead of regular tool calls.Testing & Reviewskill

157k5.8k

15Webapp Testinganthropics/skillsOfficialVerify frontend behavior, debug UI issues, capture screenshots, and inspect logs of a running local web application using Playwright.Testing & Reviewskill

151k175k

16Playwright Climicrosoft/playwright-cliOfficialRun browser automation, generate element snapshots, inspect DOM attributes, and execute Playwright tests from the terminal.Testing & Reviewskill

145k13.1k

17Playwright Best Practicescurrents-dev/playwright-best-practices-skillGet expert, context-aware guidance while writing, debugging, or scaling Playwright browser automation tests.Testing & Reviewskill

79.8k373

18Writing Guidelinesvercel-labs/agent-skillsOfficialAutomatically audit documentation, READMEs, and marketing prose against Vercel's official writing style and voice rules.Testing & Reviewskill

60.5k30.9k

19Ab Testingcoreyhaines31/marketingskillsDesign statistically sound A/B tests for headlines, CTAs, pricing pages, and landing copy before running them.Testing & Reviewskill

55.1k47.1k

20Review Loop2dmurali/review-loop-skillRun an iterative worker-reviewer loop that scores output 1-10 and revises until a quality gate is met.Testing & Reviewskill

54.9k3

21PonytailDietrichGebert/ponytailForce the simplest, shortest, most minimal solution at every step and eliminate unnecessary code, dependencies, and features.Testing & Reviewskill

52.4k128k

22Momentic Testmomentic-ai/skillsCreate, run, and maintain reliable AI-powered end-to-end browser tests without writing brittle selectors.Testing & Reviewskill

48.2k13

23Momentic Result Classificationmomentic-ai/skillsClassify, triage, and explain failures from Momentic end-to-end browser tests.Testing & Reviewskill

48.2k13

24Gsap Utilsgreensock/gsap-skillsOfficialSo their coding agent can correctly call GSAP utility methods like clamp, mapRange, normalize, snap, and random when implementing scroll-driven animations, interactiTesting & Reviewskill

47.7k15k

25Multi Account Isolationantibrow/anti-detect-browser-skillsVerify anti-detect browser profiles are truly isolated across timezone, WebRTC, canvas hashes, and cookie jars before running multi-account QA.Testing & Reviewskill

45.4k54

26Playwright Stealth Verifyliarjsdev/liarjs-skillsAssert Playwright or Puppeteer pages present a coherent browser fingerprint via liarjs library checks.Testing & Reviewskill

41.8k2

27Golang Code Stylesamber/cc-skills-golangTeach agents the idiomatic Go style that clearly signals developer intent through deliberate zero-value versus explicit initialization.Testing & Reviewskill

40.1k3.2k

30Code Review And Qualityaddyosmani/agent-skillsRun consistent multi-axis code reviews on changes produced by themselves, other agents, or humans before merging.Testing & Reviewskill

38.1k92.5k

31Golang Lintsamber/cc-skills-golangAutomatically surface correctness, style, and error-handling problems in Go code before committing.Testing & Reviewskill

37.2k3.2k

34Safe RefactorJuliusBrussee/cavemanRefactor code safely with tests, incremental steps, and rollback awareness.Testing & Reviewskill

35.9k104k

38Clerk Testingclerk/skillsOfficialReliably test authentication flows in apps that use Clerk.Testing & Reviewskill

35.5k71

39Karpathy Guidelinesmultica-ai/andrej-karpathy-skillsEmbed Andrej Karpathy’s coding principles directly into agent behavior for cleaner, simpler, and more reliable code output.Testing & Reviewskill

35.1k210k

40Vitestantfu/skillsSimulate browser APIs and edge runtimes inside Vitest test suites without spinning up real browsers.Testing & Reviewskill

34.9k5.9k

41Momentic Mobile Testmomentic-ai/skillsCreate, run, and maintain reliable end-to-end tests for Android and iOS mobile apps using real emulators and simulators.Testing & Reviewskill

34k13

42Performance Optimizationaddyosmani/agent-skillsSystematically measure, identify, fix, and validate performance bottlenecks instead of guessing.Testing & Reviewskill

32.5k92.5k

43Improveshadcn/improveSurvey any codebase as a senior advisor and generate prioritized, self-contained implementation plans that other agents can execute without additional context.Testing & Reviewskill

32.2k9.1k

44Python Testing Patternswshobson/agentsApply battle-tested patterns for testing async code, monkeypatching, temporary files, property-based tests, and database interactions in Python projects.Testing & Reviewskill

31.9k39.4k

45Documentation And Adrsaddyosmani/agent-skillsCapture architectural decisions, public API changes, and feature context so future agents and humans understand the codebase without repeated explanations.Testing & Reviewskill

31.8k92.5k

49Firecrawl Qafirecrawl/firecrawl-workflowsOfficialRun automated exploratory QA, navigation checks, form testing, and visual validation on a live website using Firecrawl.Testing & Reviewskill

31.1k151

50Test Driven Developmentaddyosmani/agent-skillsEnsure every logic change, bug fix, or behavior update is proven correct with automated tests before merging.Testing & Reviewskill

31.1k92.5k

59Code Review Excellencewshobson/agentsTurn code reviews from subjective nitpicking into structured, constructive knowledge-sharing sessions that catch bugs early and raise overall code quality.Testing & Reviewskill

27.9k39.4k

60Interview Meaddyosmani/agent-skillsExtract the real user intent behind vague or underspecified requests before writing any plans, specs or code.Testing & Reviewskill

26.6k92.5k

Explore more

By type

By what you're building

FAQ

Testing & Review tools - common questions

What are Testing & Review tools for Claude Code?

Testing & Review tools - skills, MCP servers and marketplaces tagged Testing & Review - teach Claude Code, Codex, Cursor and other coding agents how to do Testing & Review work, things like Jest, Playwright, Vitest, pytest and linting. Each one drops into your agent and installs with a single command.

How do I install a Testing & Review skill or MCP server?

Open any listing and copy its one-line command - for example npx skills add https://github.com/owner/repo --skill name for a skill, or /plugin marketplace add owner/repo for a marketplace. It's available in your next Claude Code, Codex or Cursor session.

Which Testing & Review tools and frameworks are covered?

Jest, Playwright, Vitest, pytest and linting and more. Skillselion ingests the whole catalog from skills.sh, GitHub and the MCP registries, so new Testing & Review tools appear as the community ships them - ranked by installs and GitHub stars, never paid placement.