Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full…
How to test GAIA's frontend — three tiers (vitest units, Testing Library components, Playwright e2e), the red-green-throwaway pattern for pre-merge sweeps, and the gotchas that bit us during the 2026 react-doctor sweep.
SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Write adversarial test cases that break production code instead of producing false confidence. Use when writing, reviewing, or planning tests for any codebase. Triggers on: "write tests", "add test coverage", "test this function", "create unit tests",…
Use when creating custom lint rules in Biome via GritQL plugins, writing .grit files, or debugging why plugin diagnostics are not firing on violations.
Systematically debug issues using graph-powered code navigation
Operate the running GAIA app as an agent — boot the right stack, authenticate with zero login via the dev bypass, drive the REST/SSE API and bots directly, script the LLM deterministically, and verify outcomes in Mongo instead of trusting stdout. The cookbook…