Find the perfect skill

Testing

Runs parallel external agent reviews (Codex + Gemini) on code changes, critically verifies suggestions and returns filtered, deduplicated improvements.

Testing

FakePeekskill is a fake 27-qubit backend for testing quantum circuits.

Testing

Provides automated assistance for keyboard navigation testing in frontend development, with step-by-step guidance and validation.

Testing

Organizes naive-user comprehension prompts for kid, guardian, and admin personas, tracks run scenarios, and logs responses to a dated report. Use before a release for a fresh naive-user pass.

Testing

Deep audit of ByroRedux readiness for The Elder Scrolls IV: Oblivion content, focusing on NIF format versions (v20.0.0.5 and v10.x NetImmerse tail), BSA v103, and live ESM parser.

Testing

Deep audit of NIFAL, the engine's canonical translation tier. Enforces single-boundary, no-fabrication, no-render-time-fallback rules across per-game NIF categories.

Testing

Generates realistic, correctly-linked Frappe/ERPNext test records via the bench faker CLI, then rolls them back.

Testing

Run a manual brepjs-cad skill evaluation in Claude Code: re-author playground examples, verify rendering, and get a blind judge scorecard. Propose SKILL.md fixes based on findings, no API key needed.

Testing

Implement UVM-based testbenches for hardware verification: stimulus generation, scoreboarding, coverage-driven and assertion-based testing.

Testing

Provides automated assistance for configuring test retries and best practices in test automation.

Testing

Inspect Playwright trace files from the CLI: list actions, requests, console, errors, snapshots and screenshots.

Testing

Master pytest mocking strategy: autospec vs manual mocks, AsyncMock patterns, mock factories, and what never to mock. Includes decision matrix.