Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.
Answer technical and architectural questions with expert consultation.
Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.
Feature brainstorming with Socratic questioning, design specs, and structured trade-off analysis. MANDATORY for new features, complex requests, or unclear requirements. Produces formal spec before implementation.
Technical brainstorming for architecture decisions, tech stack debates, feasibility assessment, and trade-off analysis. Use when evaluating approaches, choosing technologies, or debating technical designs.
Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.
Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion. Includes scout-based edge case detection and native Task pipeline orchestration.
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.