Find the perfect skill

Testing

Automatically generate comprehensive unit tests with edge cases, mocks, and proper assertions for any codebase.

Testing

Design and implement comprehensive evaluation systems for AI agents, covering grader types (code-based, model-based, human), benchmarks (SWE-bench, Terminal-Bench), and production integration. Use this skill when building evals for coding, conversational, research, or computer-use agents to measure and improve agent performance reproducibly.

Testing

Systematically test a web app, fix bugs found, and verify fixes with atomic commits. Produces before/after health reports and ship-readiness summary.

Testing

Skill for assembling proof kits with explicit safety justification, using artifacts and reports over narrative claims. Applies strict determinism rules and negative test suites for risky operations.

Testing

Automated assistance for creating Gatling performance test scenarios. Provides step-by-step guidance and best practices.

Testing

How to build, run and drive cv-builder to verify a change end-to-end, including dev server, Playwright recipe, data hygiene, and cleanup.

Testing

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification.

Testing

Expert in Playwright automation with Python for JSF/RichFaces applications. Uses suffix selectors, AJAX waits, and explicit viewport.

Testing

Per-game audit of Fallout 4 compatibility for ByroRedux, covering BA2, half-float verts, BGSM materials, and M49 precombines (CSG).

Testing

Black-box QA audit of slop-guard across MCP, CLI, docs, and workflows. Files genuine GitHub issues.

Testing

Runs a naive-user UX comprehension check by surfacing the next unrun prompt (kid, guardian, or admin persona) and logging the response to a dated report. Use before releases for a fresh user perspective.

Testing

CLI tool for testing and comparing LLM outputs. Create evaluation configs, test cases, and custom assertions for validating model behavior.