Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when brainstorming or planning live event technology, show control, and real-time media systems (TouchDesigner, Resolume, grandMA3).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Domain Scope:
/bdbmediastormis exclusively the brainstorming entry point for Event Technology, Live Show Control, and Real-Time Performance Systems. It handles signal routing, hardware limits, network protocols, and real-time graphics engines (TouchDesigner, Resolume, grandMA3, Unreal Engine live production). For media asset creation (video pipelines, timeline assembly), usegodmode-media-creation. For 3D mesh generation, usegodmode-3d-creation.
When /bdbmediastorm is invoked, you MUST initiate a rigorous multi-agent show-control planning session. Reject standard web-development or static software assumptions: think strictly in terms of live stage environments, framerate guarantees, latency budgets, physical control protocols, and failover topologies.
Ideation must never be performed in isolation. Spawn specialized subagents to analyze the show architecture from opposing technical angles:
Before drafting signal flow diagrams or system configs, invoke the grill-with-docs skill (or grill-me when there is no working directory) and run it to completion. Those skills hold the interview protocol — design tree, frontier rounds, numbered questions each with a recommended answer — and it is not restated here.
What this domain adds to that protocol: deeply challenge the user's technical assumptions and hardware readiness. The frontier questions for a show-control build are:
After aligning on system architecture through the grilling interview:
agent.md, signal-flow.md, network-patch.json, failover-matrix.md).The final output of a MediaStorm session must produce:
Define hardware and software nodes as strict bounded contexts:
Before this session concludes, choose the planning mode by running aos-plan-canvas modes and presenting available modes to the user (see the "Planning mode choice" section in the plan-canvas skill). Then run aos-plan-canvas open <file> --mode <choice> against signal-flow.md (or the combined show-control spec), then aos-plan-canvas await <file> and leave it running. The user reviews the signal flow diagram, hardware topology, and failover matrix in the browser (Mermaid renders live, click-to-annotate, chat rail). Do not consider the show architecture finalized before an approve verdict. A request_changes verdict means revise the artifact and reopen — it live-reloads. This is a plain CLI tool, identical regardless of which agent harness runs this skill. See the plan-canvas skill. If a build follows the approve, Trigger A starts the live map (agenttrail skill); aos-archify can render the signal flow as a workflow or architecture diagram for the review.
/bdbmediastorm strictly focused on live show control and real-time event technology.BDB MediaStorm is the master ideation and brainstorming engine for live show-control and event technology, focusing strictly on hardware constraints, signal routing, and protocol topologies.
grill-with-docs (or grill-me) to challenge assumptions about protocols, hardware, and bandwidth.agent.md, signal-flow.md, network-patch.json).| Rationalization | Reality |
|---|---|
| "We can just run NDI over the venue's Wi-Fi for testing." | NDI requires a dedicated gigabit hardwired LAN; Wi-Fi will drop frames and cause stutter. |
| "A 60fps UI is fine, we don't need a strict lock." | Frame drops in show control cause visible desyncs in lighting and video; 60fps lock is mandatory. |
| "I'll skip the blackout macro, it's just a small show." | Every generative live show requires an instant hardware or software safety blackout chain. |
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.