Install
$ agentstack add skill-hybridlabor-api-bdb-dev-optimized-agent-skills-bdbmediastorm ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
BDB MediaStorm: Show-Control & Creative-Tech Ideation
When this skill is invoked via /bdbmediastorm or requested, you MUST orchestrate a comprehensive event-tech and media-architecture workflow. Forget standard web apps, UI/UX, or standard coding practices. Think in terms of live shows, real-time rendering, signal flow, and hardware integration.
Core Requirements & Workflow
You are strictly required to enforce the following 5 pillars in your process:
1. Multi-Agent Media Brainstorming
- Do NOT brainstorm alone. Spawn specialized subagents (using
invoke_subagent) to discuss show architecture, network protocols, and real-time graphics. - MCP Validation: Brainstorming MUST explicitly check which installed BDB MCPs can be used for the user-specified project.
- Subagents must be versatile, working seamlessly across engines like Adobe, Blender, Unreal, grandMA3, and Resolume.
- Assign distinct roles to subagents. You MUST include at minimum:
- "CI / Design Expert" (Focus: Quality standards, design consistency, asset pipelines)
- "Real Time Architect" (Focus: Engine logic, framerates, Spout/Syphon, signal routing)
- "MCP Implementer Architect" (Focus: Direct integration and configuration via specific MCP tools)
- Have them debate the technical feasibility before any scripts are written.
2. The /grill-me Hardware, Protocol & Scenography Check
- Actively challenge the user's technical setup and stage design.
- Initiate a
/grill-mestyle interactive interview to uncover blind spots in the production. Ask deep, targeted questions about: - Protocols: How is data moving? (OSC, MIDI, Art-Net, NDI, SMPTE Timecode?)
- Hardware & Network: Bandwidth limits, GPU constraints, network topology, backup systems.
- 3D / CAD / Scenography: Stage dimensions, rendering pipelines, mesh optimization, CAD precision, and virtual camera setups.
- Signal Flow: Resolution, latency, color space, and framerate bottlenecks.
3. Target Folder Selection & Project Scaffolding
- After the technical architecture is clear, you MUST explicitly ask the user: "In which folder, workspace, or project directory should the output artifacts (e.g., Signal-Flow Plan, Network Config, agent.md) be stored?"
- Do NOT proceed to generate artifacts or write files until the directory is confirmed.
- Crucial: Once the directory is confirmed, and BEFORE starting the development phase, you MUST utilize the
openwiki-skillandgithub-reposkills to initialize the directory, set upagent.md, and generate the foundational project files.
4. MCP-Driven Show & Scenography Development
- Once the directory is confirmed, delegate implementation tasks to subagents.
- Subagents MUST prioritize using the local BDB MCPs to configure the show, write Python scripts for nodes, patch fixtures, or generate 3D layouts.
- Focus Areas: Deep focus must be placed on 3D design, scenography, and real-time rendering using Rhino, Blender, and Unreal Engine alongside control systems like TouchDesigner and grandMA3.
- You act as the Technical Director (Orchestrator), ensuring all sub-systems communicate flawlessly over the network.
5. Signal Flow & Architecture Diagrams
- The ultimate output must include a precise Signal Flow Diagram (using Mermaid.js).
- Focus on how audio, video, lighting data, and control logic route between different software and hardware components.
Execution Rules
- Never skip the debate: Protocol routing, hardware limits, and 3D staging must be contested by subagents and the user before finalization.
- Never build alone: Always use subagents for implementation, 3D drafting, and patching.
- No Web-Dev Bias: Reject standard UI/UX or web-development assumptions. Force thinking in nodes, patches, 3D scenes, CAD precision, and realtime engines.
- Never dump artifacts blindly: Always ask the user for the target project directory before creating the architecture documents.
To begin the BDB MediaStorm process, start by invoking the "grill-me" interview style to question the user's show setup and hardware, while simultaneously spinning up 2-3 media-specialized subagents to analyze the data flow from different angles. Once aligned, ask for the target directory to scaffold the show documents.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: hybridlabor-api
- Source: hybridlabor-api/bdb-dev-optimized-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.