Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
Guide React component design for Fogo using the Fogo design system (Industrial Warmth, dark-first, Fogo amber brand color, Tailwind CSS). Use when designing UI, creating components, styling, or writing frontend code.
Review session data model for the v2 two-phase monthly review (Reflect + Plan). Use when building review session CRUD, phase orchestration, conversation entry storage, or the review frontend. Status: BUILT (Phase 3, 2026-04-02).
Model evaluation framework for comparing LLM outputs (Haiku vs Sonnet vs fine-tuned). Use when building eval infrastructure, running model comparisons, or setting up the RLHF training pipeline. Status: PLANNED — build in Phase 2.2.
LLM Gateway interface for all Anthropic API calls in v2. Use when writing any code that calls an LLM, adding new model providers, or understanding how LLM costs are tracked. Status: PLANNED — not yet built.
Configure Buddy AI with Anthropic Claude API and set up automated insight generation via cron jobs (daily, weekly, monthly). Use when setting up Buddy AI, configuring cron jobs, or troubleshooting AI insights.
Explain code with visual diagrams and analogies. Use when explaining how code works, teaching about codebase, answering "how does this work", walking through logic, or understanding Budget Buddy architecture.
Validate Budget Buddy full-stack setup including backend/frontend connectivity, database access, CORS, environment variables, and API endpoints. Use when troubleshooting, running health checks, or diagnosing setup issues.