Find the perfect skill
Run Gallery Diff After Parser Change
Testing
Re-run the vendored gallery after a parser change and report each module's counts against its committed record, never a summary. Written after first use deliberately.
Keyboard Navigation Tester
Testing
Automated assistance for keyboard navigation testing in frontend development, providing best practices and configuration generation.
brepjs-cad Skill Evaluation
Testing
Run a brepjs-cad skill eval in the current session and propose fixes. Choose 'implement' to re-author playground examples with a blind judge, or 'verify' to run the precision/recall harness.
Adversarial Artifact Review
Testing
Adversarial review of any artifact. Assumes it is wrong and reports only surviving findings.
JavaScript Testing Patterns
Testing
Comprehensive guide for implementing robust testing strategies in JavaScript/TypeScript applications using modern testing frameworks and best practices.
brepjs-cad skill eval (manual loop)
Testing
Run a brepjs-cad skill eval in Claude Code: re-author playground examples, have a blind judge grade them, and propose SKILL.md fixes. Optional verify mode uses a precision/recall harness, no API key.
Keyboard Navigation Tester
Testing
Automated assistance for testing keyboard navigation in frontend development. Provides step-by-step guidance and best practices.
Adversarial Figure QA
Testing
Reviews rendered figures and their generating scripts to catch legend swaps, color errors, axis failures, and communication issues before sharing.
Eval Harness for Claude Code
Testing
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Define pass/fail criteria, use pass@k metrics, and track regressions.
QA Verification Harness
Testing
Runs the project's verification tiers (analyze, format, tests) after code changes, using melos and fvm.
Concurrency and Synchronization Audit
Testing
Audit ByroRedux for data races, deadlocks, incorrect lock ordering, missing Vulkan synchronization, and thread-safety violations. Focuses on GPU queue sync, ECS lock ordering, and worker thread safety.
E2E QA Test Runner
Testing
Run the E2E QA test suite against the live app using Playwright MCP and nREPL. Manages QA scripts, screenshots, and progress tracking.