Find the perfect skill

Testing

Analyzes test failures during Feature Swarm verification, diagnosing the root cause and determining if automatic recovery is possible. Provides actionable fix suggestions (e.g., missing imports, logic errors) and guides human intervention for non-recoverable issues.

Testing

Automates browser interactions using the agent-browser CLI: navigate pages, fill forms, click buttons, take screenshots, extract data, and manage authentication state. Useful for web scraping, form submissions, testing web apps, or any task requiring programmatic control of a browser. Operations are driven by element references obtained from interactive snapshots.

Testing

Specialized persona for test architecture and quality assurance. Provides personalized testing guidance and best practices.

Testing

Read-oriented inspection of completed work or artifacts for drift, inconsistency, omissions, or unsupported claims.

Testing

Automate VS Code (Code OSS) using agent-browser via Chrome DevTools Protocol. Interact with the chat panel, test UI features, and take screenshots.

Testing

Run a manual brepjs-cad skill evaluation in the Claude session and propose fixes, no API key. Implement or verify playground examples with blind-judge scoring.

Testing

Deep audit of ByroRedux readiness for The Elder Scrolls IV: Oblivion, covering NIF v20.0.0.5, v10.x NetImmerse tail, BSA v103, and live ESM parsing.

Testing

Run a brepjs-cad skill eval in-session: re-author playground examples, verify/render, and use a blind judge to score and find SKILL.md gaps.

Testing

Independently audit an Angular component spec file against project migration guidelines.

Testing

Analyzes Java runtime issues including stack traces, exceptions, thread dumps, and performance problems to identify root causes and provide actionable solutions. Helps debug common errors like NullPointerException, memory leaks, and concurrency issues. Use when troubleshooting production errors or logs.

Testing

Test React components with React Testing Library and Playwright. Cover unit tests, user interactions, and E2E testing.

Testing

Retroactively audits an executed AI phase's evaluation coverage, scores each dimension, and produces an actionable EVAL-REVIEW.md with remediation plan.