NAJEMWEHBE

Captures lessons during a session and promotes recurring ones into persistent rules. Use when the user corrects Claude, a tool fails, an assumption was wrong, a capability is missing, or a better approach is found — and at session start to review existing lessons in the domain.

Live streaming operations using a bonding router and SRT/RTMP relay servers. Use when configuring OBS, planning a stream, troubleshooting bitrate/jitter issues, deciding which uplink combination to use, or briefing a client on streaming constraints. Also use before any live event involving streaming setup.

Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot, taking viewport or off-screen renders, auditing or compiling blueprints, or doing asset hygiene (find/move/rename/delete/fix-up redirectors). Teaches which tools to chain, in what order, the verification checkpoints, and the UE 5.x traps that silently no-op or corrupt state. Routes through the MCP server named "unreal-ai-connection" (tools are exposed as mcp__unreal-ai-connection__<tool>; confirm with list_tools). Trigger phrases: "Unreal", "Unreal Engine", "UE5", "UE 5.7", "build a level", "populate the level", "spawn an actor", "place actors", "apply a material", "material instance", "set up a sequencer shot", "cinematic", "screenshot the viewport", "render the scene", "photo to Unreal", "compil

Answer "what do I have for X?" from the owner's studied tool catalog (skills/plugins/agents/models with use_when/avoid_when). Use when they ask what tool/skill/plugin they have for a need, whether something exists in their arsenal, "do I have something for...", "which of my tools...", or want a specific tool explained ("what does X do?", "when do I use X?").

A multi-team, multi-tool agentic engine that orchestrates parallel worker groups (Intelligence, Execution, QA) to solve complex technical problems, using a consensus stability gate and an ELO tournament to select and ship the single best solution. Trigger when the user says "solve:", /problem-solver, or asks to generate several competing solutions and pick the best.

Run a health check on the AI coding stack — verify the agent CLI, MCP servers, memory system, API keys, and runtimes are actually WORKING (not just installed). Use when the user says "/doctor", "health check", "check my setup", "is X working", "diagnose my environment", "why is memory/MCP not working", or after install/config changes.