agentskillexchange Turn a plain-language brief into a multi-step video production pipeline with OpenMontage
Use OpenMontage when an agent should take a brief or reference video and run the research, scripting, asset generation, editing, subtitle, and render pipeline as one production workflow instead of treating each media tool as a separate manual step.
Prerequisites
Python 3.10+, Node.js 18+, FFmpeg, an AI coding assistant or agent runtime, and whichever media/model providers the chosen pipeline needs
Installation
Requirements and caveats from upstream:
- Agent calls Python tools -- scored provider selection ranks every tool across 7 dimensions
- Python provides tools and persistence. All creative decisions, orchestration logic, review criteria, and quality standards live in readable instruction files (YAML manifests + Markdown skills) that you can inspect...
- | Remotion | Local (Node.js) | React-based programmatic video — spring-animated image scenes, stat reveals, section titles, hero cards, TikTok-style word-by-word captions, scene transitions (fade/slide/wipe/flip),...
Basic usage or getting-started notes:
Quick Start ·
Works with Claude Code, Cursor, Copilot, Windsurf, Codex — any AI coding assistant that can read files and run code.
Coming soon: Local LLM support via Ollama and LM Studio — run the full production pipeline without any cloud LLM.
Extracted from upstream docs: https://raw.githubusercontent.com/calesthio/OpenMontage/HEAD/README.md