Find the perfect skill

Testing

Run a manual brepjs-cad skill evaluation: re-author playground examples and judge them blindly, or verify precision/recall, then propose SKILL.md fixes. No API key needed.

Testing

Runs naive-user comprehension tests for a web app by managing prompt scenarios and logging results to dated reports. Use before release for a fresh-user perspective.

Testing

Audits the DPCM/drum subsystem: MIDI mapping, WAV-to-NES delta conversion, and DMC channel driving. Verifies hardware constraints and regressions.

Testing

Run a manual eval loop for the brepjs-cad implement skill: re-author playground examples, have a blind judge grade them, and propose SKILL.md fixes. No API key required.

Testing

Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement.

Testing

Run a named preset of audit commands in parallel and merge their reports into one summary. Coordinates background agents; no audit logic itself.

Testing

Systematically test a web application, fix bugs found, and re-verify. Supports quick, standard, and exhaustive tiers with before/after health scores.

Testing

Automated assistance skill for configuring test retries within test automation workflows (Jest, Pytest, etc.).

Testing

Prioritizes visual stability over perfection. Flags only issues that could cause embarrassment during a live demo. Use when preparing for demos, final pre-deploy review, or verifying demo-critical paths.

Testing

Master mocking strategy for pytest: when to use autospec vs manual mocks, AsyncMock patterns, and what should never be mocked. Includes decision matrix.

Testing

Run the project's verification harness (analyze, lint, format, tests) after code changes. Supports quick, standard, and full tiers.

Testing

Audit the pattern-detection and compression subsystem for round-trip integrity, schema, and parallelism. Verify lossless compression and correct decompression of patterns and references.