# Skills for Testing and QA Skills for Testing and QA: what each one does, an install command and example prompts. 1556 cards · page 1 of 39 - HTML: https://affpapa.org/en/nevibecode/skills/topic/testing - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [improve-codebase-architecture](https://affpapa.org/en/nevibecode/skills/improve-codebase-architecture.md) — skill · Matt Pocock · Claude Code · 1163035 installs — This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. - [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · Leonxlnx · Claude Code, Codex, Cursor +3 · 678700 installs — This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. - [tdd](https://affpapa.org/en/nevibecode/skills/tdd.md) — skill · Matt Pocock · Claude Code · 1141062 installs — Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. - [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill (official Anthropic) · anthropics · Claude Code, Claude.ai · 414180 installs — Creates and refines skills, then tests them with prompts, evaluations, and performance checks. - [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · vercel-labs · Claude Code, Codex, Cursor +3 · 1200000 installs — A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. - [prototype](https://affpapa.org/en/nevibecode/skills/prototype.md) — skill · Matt Pocock · Claude Code · 986201 installs — Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. - [codebase-design](https://affpapa.org/en/nevibecode/skills/codebase-design.md) — skill · Matt Pocock · Claude Code · 850344 installs — This skill helps design modules with small interfaces and hidden complexity. - [diagnosing-bugs](https://affpapa.org/en/nevibecode/skills/diagnosing-bugs.md) — skill · Matt Pocock · Claude Code · 834802 installs — This skill guides agents through reproducing hard bugs and performance regressions with a focused feedback loop. - [implement](https://affpapa.org/en/nevibecode/skills/implement.md) — skill · Matt Pocock · Claude Code · 774700 installs — Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. - [to-spec](https://affpapa.org/en/nevibecode/skills/to-spec.md) — skill · Matt Pocock · Claude Code · 715388 installs — Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. - [setup-pre-commit](https://affpapa.org/en/nevibecode/skills/setup-pre-commit.md) — skill · Matt Pocock · Claude Code · 489289 installs — This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit. - [webapp-testing](https://affpapa.org/en/nevibecode/skills/webapp-testing.md) — skill (official Anthropic) · anthropics · Claude Code, Claude.ai · 186758 installs — This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs. - [migrate-to-shoehorn](https://affpapa.org/en/nevibecode/skills/migrate-to-shoehorn.md) — skill · Matt Pocock · Claude Code · 475388 installs — Replaces as type assertions in tests with helpers from @total-typescript/shoehorn. - [systematic-debugging](https://affpapa.org/en/nevibecode/skills/systematic-debugging.md) — skill · Jesse Vincent · Claude Code, Codex · 306118 installs — Makes the agent investigate the cause of a failure before it suggests a patch. - [requesting-code-review](https://affpapa.org/en/nevibecode/skills/requesting-code-review.md) — skill · Jesse Vincent · Claude Code, Codex · 262135 installs — Sends completed work to a reviewer subagent after a task, major feature, or before merging to main. - [test-driven-development](https://affpapa.org/en/nevibecode/skills/test-driven-development.md) — skill · Jesse Vincent · Claude Code, Codex · 259292 installs — This skill guides an agent through test-first development: verify a test fails, write the smallest passing change, then refactor. - [verification-before-completion](https://affpapa.org/en/nevibecode/skills/verification-before-completion.md) — skill · Jesse Vincent · Claude Code, Codex · 251313 installs — This skill blocks completion claims until the agent runs a fresh check and reads the result. - [executing-plans](https://affpapa.org/en/nevibecode/skills/executing-plans.md) — skill · Jesse Vincent · Claude Code, Codex · 242988 installs — Runs an implementation plan in the current session instead of assigning each task to a subagent. - [receiving-code-review](https://affpapa.org/en/nevibecode/skills/receiving-code-review.md) — skill · Jesse Vincent · Claude Code, Codex · 221216 installs — Reviews code review feedback before changes: it clarifies unclear points, checks the repository, and supports reasoned pushback. - [dispatching-parallel-agents](https://affpapa.org/en/nevibecode/skills/dispatching-parallel-agents.md) — skill · Jesse Vincent · Claude Code, Codex · 218235 installs — Dispatches independent tasks to separate subagents so they can investigate them in parallel. - [writing-skills](https://affpapa.org/en/nevibecode/skills/writing-skills.md) — skill · Jesse Vincent · Claude Code, Codex · 217894 installs — Applies a TDD workflow to authoring and checking agent skills: observe failure first, then write instructions that address it. - [using-git-worktrees](https://affpapa.org/en/nevibecode/skills/using-git-worktrees.md) — skill · Jesse Vincent · Claude Code, Codex · 217153 installs — Prepares an isolated workspace before feature work or plan execution. - [finishing-a-development-branch](https://affpapa.org/en/nevibecode/skills/finishing-a-development-branch.md) — skill · Jesse Vincent · Claude Code, Codex · 214439 installs — This skill checks the test suite and guides branch completion: merge locally, open a Pull Request, or leave the work in place. - [implement-spec](https://affpapa.org/en/nevibecode/skills/implement-spec.md) — skill · Matt Pocock · Claude Code · 283700 installs — Implements a prepared spec from its ticket graph on one integration branch, using parallel subagents. - [retro](https://affpapa.org/en/nevibecode/skills/retro.md) — skill · Matt Pocock · Claude Code · 276027 installs — Reviews a coding session and suggests changes to the agent environment for later runs. - [remotion-to-hyperframes](https://affpapa.org/en/nevibecode/skills/remotion-to-hyperframes.md) — skill · heygen-com · Claude Code, Codex, Cursor +3 · 510300 installs — Imports Remotion animations or video footage into HyperFrames and verifies visual matching frame by frame against the original. - [google-agents-cli-eval](https://affpapa.org/en/nevibecode/skills/google-agents-cli-eval.md) — skill (official Google) · Google · Claude Code, Codex, Cursor +3 · 511400 installs — Guides testing, dataset setup, and scoring for AI agents via agents-cli. - [google-agents-cli-workflow](https://affpapa.org/en/nevibecode/skills/google-agents-cli-workflow.md) — skill (official Google) · Google · Claude Code, Codex, Cursor +3 · 511400 installs — This skill guides ADK agent work from scaffolding through deployment and observability. - [ponytail](https://affpapa.org/en/nevibecode/skills/ponytail.md) — skill · DietrichGebert · Claude Code, Codex, Cursor +3 · 106200 installs — ponytail puts an agent into a senior-dev mode focused on the smallest complete change. - [browser-use](https://affpapa.org/en/nevibecode/skills/browser-use.md) — skill · browser-use · Claude Code, Codex, Cursor +3 · 98200 installs — Hands the agent a real Chrome over CDP: clicks, typing, screenshots, and pages that need JS or your logged-in session. - [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · DietrichGebert · Claude Code, Codex, Cursor +3 · 57000 installs — ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. - [playwright-cli](https://affpapa.org/en/nevibecode/skills/playwright-cli.md) — skill · microsoft · Claude Code, Codex, Cursor +3 · 195700 installs — A skill that hands your agent a browser: open a page, click elements, grab a snapshot, and work with Playwright tests. - [caveman-optimize](https://affpapa.org/en/nevibecode/skills/caveman-optimize.md) — skill · JuliusBrussee · Claude Code, Codex, Cursor +3 · 105800 installs — This skill turns a Caveman report observation into an operator-selected candidate and a paired baseline evaluation. - [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · DietrichGebert · Claude Code, Codex, Cursor +3 · 45400 installs — It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. - [investigate-first](https://affpapa.org/en/nevibecode/skills/investigate-first.md) — skill · JuliusBrussee · Claude Code, Codex, Cursor +3 · 105400 installs — The skill keeps the agent in diagnosis mode: gather evidence, rank hypotheses, name the cause. - [verify-and-stop](https://affpapa.org/en/nevibecode/skills/verify-and-stop.md) — skill · JuliusBrussee · Claude Code, Codex, Cursor +3 · 104900 installs — Proves existing work meets acceptance criteria without expanding scope. - [surgical-patch](https://affpapa.org/en/nevibecode/skills/surgical-patch.md) — skill · JuliusBrussee · Claude Code, Codex, Cursor +3 · 104800 installs — The skill constrains AI coding agents to the narrowest layer responsible for a bug. - [caveman-manage](https://affpapa.org/en/nevibecode/skills/caveman-manage.md) — skill · JuliusBrussee · Claude Code, Codex, Cursor +3 · 104200 installs — Checks Caveman Cloud experiment state and evidence, then recommends one action or blocks an unsafe request. - [code-review-and-quality](https://affpapa.org/en/nevibecode/skills/code-review-and-quality.md) — skill · addyosmani · Claude Code, Codex, Cursor +3 · 73200 installs — Five review axes and a limit on diff size, so an agent checks a change before merge instead of after. - [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · addyosmani · Claude Code, Codex, Cursor +3 · 70200 installs — Guides threat modeling and security checks for code that handles user input, authentication, sessions, or external services. Next: https://affpapa.org/en/nevibecode/skills/topic/testing.md?page=2 ## Refine [qa](https://affpapa.org/en/nevibecode/tag/qa.md) · [debugging](https://affpapa.org/en/nevibecode/tag/debugging.md) · [ci-cd](https://affpapa.org/en/nevibecode/tag/ci-cd.md) · [python](https://affpapa.org/en/nevibecode/tag/python.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [e2e](https://affpapa.org/en/nevibecode/tag/e2e.md) · [tdd](https://affpapa.org/en/nevibecode/tag/tdd.md) · [ios](https://affpapa.org/en/nevibecode/tag/ios.md) · [accessibility](https://affpapa.org/en/nevibecode/tag/accessibility.md) · [dotnet](https://affpapa.org/en/nevibecode/tag/dotnet.md) · [java](https://affpapa.org/en/nevibecode/tag/java.md) · [react](https://affpapa.org/en/nevibecode/tag/react.md) ## Narrow this list Parameters: `?platform=`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md