Find the perfect skill

Testing

Runs the Dart/Flutter verification harness (analyze, format, tests) after code changes, with three tiers: quick, standard, and full.

Testing

Direct-entry shortcut to author new tests (unit/integration/e2e), each traced to an acceptance criterion. Skips triage and runs the shortcut engine to produce a graded work halting for approval.

Testing

This skill tests the shallow namespace generation for skills at the first level under the skills/ directory. It is used to verify that the skill's flattened name matches the expected pattern and to compare with deeper nesting scenarios.

Testing

Review code for potential issues and improvements, following a rigorous methodology with subagents and evidence-based reporting.

Testing

Automate accessibility testing with axe-core, pa11y, and custom WCAG compliance checks.

Testing

Master mocking strategy for pytest: when to use autospec=True vs manual mocks, AsyncMock patterns, and what should never be mocked. Includes type-safe mock creation and decision matrix.

Testing

Formal evaluation framework for Claude Code sessions implementing eval-driven development. Defines pass/fail criteria, grader types, and metrics like pass@k for measuring agent reliability.

Testing

Audit ByroRedux for data races, deadlocks, incorrect lock ordering, missing Vulkan synchronization, and thread-safety violations.

Testing

Single-pass quality assessment for code, documents, API responses, test output. Provides score, verdict, suggestions.

Testing

Automate browser interactions using agent-browser CLI — navigate, click, fill forms, scrape content, take screenshots, and more.

Testing

Manage snapshot tests for UI components with smart diff detection and automated update workflows.

Testing

Validate all checkpoints from an agent run directory in parallel. Spawns test-validator agents for each checkpoint and summarizes results.