Skill pack · Free

Testing & QA Pack

Test-first development, real-browser checks and adversarial review of an agent’s own work.

5 skills 3 repositories MIT All work with Claude Code, Codex, Cursor

Who it’s for: Teams who want an agent to prove its changes work before handing them over.

The most common failure of coding agents is declaring success too early. This pack makes verification part of the job: tests first, checks in a real browser, and a second look at non-trivial decisions.

Skills in this pack

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

↑ GrowingActive Claude CodeCodexCursor+1
98k GitHub stars MIT Updated Sep 20, 2026 Free

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

🔥 TrendingActive Claude CodeCodexCursor+1
98k GitHub stars MIT Updated Sep 20, 2026 Free

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

↑ GrowingActive Claude CodeCodexCursor+1
98k GitHub stars MIT Updated Sep 20, 2026 Free

Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.

↑ GrowingActive Claude CodeCodexCursor+2
47k GitHub stars MIT Updated Sep 21, 2026 Free

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.

Claude CodeCodexCursor+1
25k GitHub stars MIT Updated Aug 17, 2026 Free

Install

Run these commands in your agent. Plugin marketplace commands work in Claude Code; the git clone commands copy a skill into Claude Code’s personal skills folder — adjust the path for other agents.

/plugin marketplace add addyosmani/agent-skills
/plugin marketplace add sickn33/agentic-awesome-skills
/plugin marketplace add alirezarezvani/claude-skills

Review each skill’s source before installing. Every skill links to its repository above.

More packs

All packs →

Custom skills

Need this adapted to your team?

We can tailor these skills to your conventions and tools, or build the missing piece of your workflow as a new skill.

Frequently asked questions

What is in the Testing & QA Pack?
5 skills: test-driven-development (by addyosmani), browser-testing-with-devtools (by addyosmani), doubt-driven-development (by addyosmani), agent-evaluation (by sickn33), a11y-audit (by alirezarezvani). They come from 3 repositories.
Is this pack free?
Yes. Every skill in it is free to install from its public GitHub repository. Licenses in this pack: MIT.
Do I have to install every skill?
No. Each skill works on its own; install the ones your project needs. Installing a plugin marketplace adds every skill in that repository.