kanban-video-orchestrator

Plan and run multi-agent video production pipelines through a ZeusAgent kanban board.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/loteiron/ZeusAgent --skill kanban-video-orchestrator-loteiron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kanban-video-orchestrator
Source: https://github.com/loteiron/ZeusAgent/tree/main/optional-skills/creative/kanban-video-orchestrator
Command: npx skills add https://github.com/loteiron/ZeusAgent --skill kanban-video-orchestrator-loteiron

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Coordinating a multi-scene video project across different rendering tools, audio sources, and review steps is error-prone when done ad hoc. This Skill wraps any video request in a structured kanban pipeline that decomposes the work across specialized agent profiles with a shared workspace. ## Core Features & Use Cases - Adaptive Discovery and Briefing: Asks targeted intake questions per video style, then produces a structured brief.md that acts as the contract for all downstream tasks. - Team Design and Setup Generation: Composes a team of role archetypes (director, writer, renderers, editor, reviewer) and generates a setup.sh that creates ZeusAgent profiles, SOUL.md files, and the initial kanban task. - Monitoring and Intervention: Polls the kanban for stuck tasks, missing heartbeats, and retries, with documented recipes for re-renders, dependency changes, and brief pivots. - Use Case: A user requests a 3-minute music video synced to a provided track. The Skill scopes the brief, designs a team with a music-supervisor producing beats.json plus ASCII and p5.js renderers, bootstraps the workspace, and monitors the pipeline to the final cut. ## Quick Start Ask the agent to plan and run a video production pipeline for your video idea, providing the length, aspect ratio, and target platform.

Frequently Asked Questions about kanban-video-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate a multi-agent video production pipeline?▼

Run adaptive discovery to classify the video style, produce a brief.md contract, design a team of role archetypes, then generate and run a setup.sh that creates ZeusAgent profiles and fires the initial kanban task to the director profile.

What rendering tools can a video pipeline team use?▼

Renderer profiles load skills such as ascii-video, manim-video, p5js, comfyui, touchdesigner-mcp, pixel-art, or baoyu-comic, or call external APIs like Runway, Kling, ElevenLabs, and Remotion from the terminal toolset.

When should I not use a kanban video pipeline?▼

Skip it for single-tool procedural videos, one-shot conversions like mp4-to-GIF via ffmpeg, static images or audio-only artifacts, and any job that fits one existing skill cleanly such as a pure ASCII video.

Why do kanban video tasks fail to share artifacts between profiles?▼

Artifact sharing breaks when tasks omit workspace_kind="dir" and an absolute workspace_path, or use mismatched tenants. Every kanban_create call must pass the shared project directory and the project-specific tenant slug.

How do I monitor and fix stuck video render tasks?▼

Poll the board with zeus kanban list or the monitor.py script, which flags tasks with no heartbeat in two minutes, overtime runs, and repeated retries. Intervene by commenting with feedback, creating a re-run task, or blocking and archiving the stuck task.

What API keys does a video production pipeline need?▼

Keys depend on the team: ELEVENLABS_API_KEY for voiceover, OPENROUTER_API_KEY for video review, FAL_KEY or REPLICATE_API_TOKEN for image generation, and RUNWAY_API_KEY or KLING_API_KEY for image-to-video. The setup script verifies keys before firing the kanban.