Systematically extract knowledge from scattered documentation to prevent catastrophic forgetting. Creates structured extraction reports with status tags.
Research using ONLY knowledge graph semantic search (no file tools, forces KG-first approach)
Guide for using /compact (Claude Code built-in) with the pre-compact save pipeline. Shows what gets saved before compression and what gets reinjected after.
Expert guidance on cross-domain architecture decisions, technology selection, and infrastructure design requiring deep analysis of tradeoffs and long-term implications
Expert guidance on RAG (Retrieval-Augmented Generation) system design including chunking strategies, embedding selection, retrieval methods, and vector database choices
Quick guidance on choosing AI models (LLM/VLM/Embedding) based on task, VRAM, cost, and quality requirements
Expert guidance on database design, schema optimization, query performance, and database technology selection
Quick VRAM/RAM calculations, hardware recommendations, feasibility checks for AI models
Analyzes project workflow setup and suggests/creates needed automation for hooks, scripts, skills, and agents
Automated visual testing with Playwright MCP - test web apps, presentations, websites, and documents with scalable reviewer perspectives
Documentation templates - README, API docs, ADRs, user guides
Quick GUI/UX/UI design consultations and recommendations