--- title: Top Testing & QA Skills for Cursor slug: top-testing-qa-skills-for-cursor type: category-agent-cut category: testing-qa agent: cursor canonical: https://top-agent-skills.com/top-testing-qa-skills-for-cursor verified: 7 unverified: 5 updated: 2026-07-15 --- # Top Testing & QA Skills for Cursor For testing in Cursor, start with Anthropic's webapp-testing skill for driving a real browser against a running app, add playwright-skill if your suite is already Playwright-based, and use tdd-skill when you want tests written before the implementation. Anthropic's verify skill is the cheap one to install first — it makes the agent actually check its work instead of declaring success. ## Verified on Cursor (7) ### 1. debug — score 51/100 (official-anthropic) Disciplined debugging loop. Reproduce, isolate, diagnose, fix. - Best for: When behavior diverges from expected and the cause is not obvious from a quick read. - Publisher: Anthropic · MIT - Verified on: claude-code, cursor, codex, antigravity ```bash claude plugin install engineering ``` Full entry: https://top-agent-skills.com/skill/debug (https://top-agent-skills.com/skill/debug.md) ### 2. testing-strategy — score 51/100 (official-anthropic) Layered test plan sized to the change's risk profile. - Best for: Greenfield features when you need a real plan before writing the first test. - Publisher: Anthropic · MIT - Verified on: claude-code, cursor, codex, antigravity ```bash claude plugin install engineering ``` Full entry: https://top-agent-skills.com/skill/testing-strategy (https://top-agent-skills.com/skill/testing-strategy.md) ### 3. webapp-testing — score 50/100 (official-anthropic) Test local webapps with Playwright. Generation, run, report — end-to-end. - Best for: Filling test gaps in a webapp, smoke-testing UIs after a change. - Publisher: Anthropic · MIT - Verified on: claude-code, cursor ```bash npx skills add github.com/anthropics/skills --skill webapp-testing ``` Full entry: https://top-agent-skills.com/skill/webapp-testing (https://top-agent-skills.com/skill/webapp-testing.md) ### 4. verify — score 50/100 (official-anthropic) Real feature verification — run the app, drive it, prove it works. - Best for: Pre-merge verification for UI changes when type checks and unit tests verify code, not feature correctness. - Publisher: Anthropic · MIT - Verified on: claude-code, cursor Install: Built into Claude Code. Invoke with /verify. Full entry: https://top-agent-skills.com/skill/verify (https://top-agent-skills.com/skill/verify.md) ### 5. agent-browser — score 47/100 (verified-org) Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions. - Best for: When you need browser automation that does not rely on clean APIs and survives selector churn. - Publisher: Vercel Labs · Apache-2.0 - Verified on: claude-code, cursor ```bash npm install -g agent-browser ``` Full entry: https://top-agent-skills.com/skill/agent-browser (https://top-agent-skills.com/skill/agent-browser.md) ### 6. tdd-skill — score 46/100 (community) TDD with red/green/refactor as a concrete TypeScript walkthrough. Full entry: https://top-agent-skills.com/skill/tdd-skill (https://top-agent-skills.com/skill/tdd-skill.md) ### 7. playwright-skill — score 40/100 (community) Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults. Full entry: https://top-agent-skills.com/skill/playwright-skill (https://top-agent-skills.com/skill/playwright-skill.md) ## In Testing & QA but NOT verified on Cursor (5) These may well work — the SKILL.md format is shared. They are listed as unverified because this site lists an agent only where the install was run or the publisher documents a path for it. - ios-simulator-skill — Drive the iOS Simulator from the agent loop. Build and test iOS apps. (https://top-agent-skills.com/skill/ios-simulator-skill) - playwright-cli — Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required. (https://top-agent-skills.com/skill/playwright-cli) - ui-test — Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX. (https://top-agent-skills.com/skill/browserbase-ui-test) - chrome-devtools — Chrome's own team, giving agents the DevTools protocol: drive it, inspect it, debug it. (https://top-agent-skills.com/skill/chrome-devtools) - run — One-command app launch tailored to your project type. (https://top-agent-skills.com/skill/run) ## Common question **Do browser-testing skills work with Cursor, or do they need a terminal agent?** They work where the agent can run a local process and reach a dev server. Cursor can, so the skills are verified here — but the skill supplies the testing method and Playwright conventions, not the browser. Install the runtime (Playwright browsers) once, separately, as you would for any local test suite. --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/top-testing-qa-skills-for-cursor._