Design tool interfaces for LLM agents — descriptions, parameter schemas, error messages, granularity, and composition. Use when creating function calling tools, building MCP servers, designing agent tool interfaces, writing tool descriptions, or debugging why a model calls the wrong tool, hallucinates parameters, or…
Browser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR recording over CDP. Use when validating UI state, testing features in the browser, or manipulating a running web app.
Diagnose root cause of an issue using adaptive multi-perspective investigation. Use when debugging bugs, errors, test failures, or unexpected behavior — especially intermittent, cross-module, or "stuck" problems where a single-pass read isn't enough.
Systematic debugging methodologies for hard bugs. Covers rubber ducking, code tracing, hypothesis testing, logging strategies. Use when stuck on bugs that resist quick fixes.
Test writing and fixing methodology. Covers TDD, investigating failures, and delegating fixes to agents. Use when writing tests or diagnosing test failures.