--- title: Top Testing & QA Skills slug: testing-qa type: primary-category canonical: https://top-agent-skills.com/top-skills-for-testing-qa skills: 12 rubric: 1.0 updated: 2026-08-25 --- # Top Testing & QA Skills **playwright-cli** is the top-ranked testing Skill at 60/100: Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required. Webapp testing, Playwright flows, browser test runners, and automated QA passes. 12 Skills indexed, ranked by a published composite score (https://top-agent-skills.com/about/methodology). Content last changed 2026-08-25. ## The ranking ### 1. playwright-cli — score 60/100 (verified-org) Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required. - Best for: Driving a real browser from the agent and working with an existing Playwright suite — navigation, assertions, tracing, video, request mocking, and test generation. - Not ideal for: Hosted scraping at scale. It drives a local browser, so rate limiting and anti-bot handling are your problem — reach for a hosted extraction skill when the target fights back. - Publisher: Microsoft · Apache-2.0 - Verified on: claude-code ```bash playwright-cli install --skills ``` Full entry: https://top-agent-skills.com/skill/playwright-cli (https://top-agent-skills.com/skill/playwright-cli.md) ### 2. ui-test — score 58/100 (verified-org) Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX. - Best for: QA on a pull request, where testing the whole app is too slow and testing nothing is what actually happens. - Not ideal for: Deterministic regression suites. It explores and spawns sub-agents with step budgets, so results vary between runs — use it alongside a fixed suite, not instead of one. - Publisher: Browserbase · MIT (declared in SKILL.md frontmatter; no repo LICENSE file) - Verified on: claude-code ```bash npx skills add browserbase/skills ``` Full entry: https://top-agent-skills.com/skill/browserbase-ui-test (https://top-agent-skills.com/skill/browserbase-ui-test.md) ### 3. chrome-devtools — score 57/100 (verified-org) Chrome's own team, giving agents the DevTools protocol: drive it, inspect it, debug it. - Best for: Debugging a live page — performance, accessibility, memory, or why a flow breaks in a real browser. - Not ideal for: Large-scale scraping of blocked sites; that is what the proxy-based scraping skills exist for. - Publisher: Chrome DevTools (Google) · Apache-2.0 - Verified on: claude-code ```bash /plugin marketplace add ChromeDevTools/chrome-devtools-mcp ``` Full entry: https://top-agent-skills.com/skill/chrome-devtools (https://top-agent-skills.com/skill/chrome-devtools.md) ### 4. 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) ### 5. 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) ### 6. webapp-testing — score 50/100 (official-anthropic) Test local webapps with Playwright. Generation, run, report — end-to-end. Full entry: https://top-agent-skills.com/skill/webapp-testing (https://top-agent-skills.com/skill/webapp-testing.md) ### 7. verify — score 50/100 (official-anthropic) Real feature verification — run the app, drive it, prove it works. Full entry: https://top-agent-skills.com/skill/verify (https://top-agent-skills.com/skill/verify.md) ### 8. run — score 48/100 (official-anthropic) One-command app launch tailored to your project type. Full entry: https://top-agent-skills.com/skill/run (https://top-agent-skills.com/skill/run.md) ### 9. agent-browser — score 47/100 (verified-org) Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions. Full entry: https://top-agent-skills.com/skill/agent-browser (https://top-agent-skills.com/skill/agent-browser.md) ### 10. 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) ### 11. ios-simulator-skill — score 41/100 (community) Drive the iOS Simulator from the agent loop. Build and test iOS apps. Full entry: https://top-agent-skills.com/skill/ios-simulator-skill (https://top-agent-skills.com/skill/ios-simulator-skill.md) ### 12. 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) ## About this category The best agent skill for testing and QA in 2026 is verify — it launches your project's dev server, drives the changed feature through a real browser, and returns screenshots and console logs as proof the change works, replacing the ritual of asking "did it work?" with observed behavior. Testing & QA Skills give agents the disciplined harness needed to actually verify a change works — not claim success because the types compile. The canonical Skill here is verify, which launches the project's dev server, drives the feature in a browser, and reports back with screenshots and console logs. Other top-ranked Skills handle test-strategy design, Playwright authoring, browser-automation flows, mocked vs. real-database integration testing, and structured test plans for new features. These Skills shine on three workflows: pre-merge verification (run the app, click through the change, screenshot the result), test authoring (Playwright flows, API contract tests, snapshot tests), and broader test strategy (deciding what to test at what layer for a new feature). They are particularly valuable for UI changes where the agent cannot otherwise see what it built. The lesson from the community is brutal: type checking and npm test verify code correctness, not feature correctness. Real verification means running the app. QA engineers, full-stack developers, and engineering teams shipping daily depend on these. Composite scoring here weights install ergonomics heavily — a verify Skill that requires twenty minutes of Playwright setup loses to one that auto-detects the project's dev command. Anthropic-authored Skills (verify, testing-strategy) and high-install Playwright Skills dominate the top of the ranking. ## Common questions **What does the verify Skill do?** It launches the project's dev server, navigates to the changed page, drives the feature using preview tools (click, fill, snapshot), and reports back with proof — screenshots, network logs, console output. It replaces the ritual of asking "did it work?" with observed behavior. **Do I need Playwright installed?** Not for verify — it uses Claude Code's built-in preview MCP. For authoring durable browser tests, the Playwright Skills set up the test runner and write the first specs. **How do testing Skills choose what to test?** The testing-strategy Skill walks the codebase and proposes a layered test plan — unit for pure logic, integration for boundaries, end-to-end for critical user flows — sized to the feature's risk profile. **Can these Skills run tests in CI?** They author the tests; CI runs them. Several Skills generate GitHub Actions configs that wire the new tests into the existing pipeline. **Mock the database or hit a real one?** The top-ranked Skills default to real databases for integration tests — mock/prod divergence is a well-known source of bugs that pass tests and fail production migrations. Unit tests stay mocked. --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/top-skills-for-testing-qa._ _JSON: https://top-agent-skills.com/top-skills-for-testing-qa.json · whole catalog: https://top-agent-skills.com/skills.json (CC BY 4.0)_