# OpenMontage Documentary Montage — workflow skill for AI editing agents

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

Builds a CLIP-searchable corpus from free archives (Pexels, Archive.org, NASA, Wikimedia, Unsplash) and cuts real footag

- **Type:** [Workflow](https://varg.ai/how-to/workflows.md) · [AI editing agents](https://varg.ai/how-to/browse/skills/edit-agents.md)
- **Slug:** `openmontage-documentary-montage`
- **Status:** live
- **Publisher:** Calesthio (community)
- **License:** AGPL-3.0
- **Source:** https://github.com/calesthio/OpenMontage/tree/main/skills/pipelines/documentary-montage/
- **Works in:** Claude Code, Codex, Cursor, OpenClaw
- **Requires:** Python 3.10+, ffmpeg, Node.js 18+, an AI coding assistant
- **Cost:** Free/open source; generation billed by providers you connect

## What it does

Builds a CLIP-searchable corpus from free archives (Pexels, Archive.org, NASA, Wikimedia, Unsplash) and cuts real footage by narrative beat with music sync and a unified grade. One of OpenMontage's 12 production pipelines: a YAML manifest (`pipeline_defs/documentary-montage.yaml`) plus per-stage director skills in `skills/pipelines/documentary-montage/` that the agent reads before it calls the repo's Python tools (ffmpeg, WhisperX, scene detection, face-tracked reframe, Remotion or HyperFrames rendering). It checkpoints state, stops for approval at creative gates and self-reviews the render with ffprobe, frame samples and audio levels. Open the OpenMontage folder in your agent and ask for this kind of edit; the agent routes to the pipeline.

## Use when

- Asked for a documentary montage edit of footage you already have
- Want a staged pipeline with approval gates instead of one prompt

## Not for

- A single drop-in skill (it runs inside the OpenMontage repo)

## Install

- Claude Code: `git clone https://github.com/calesthio/OpenMontage.git && cd OpenMontage && make setup`

## More AI editing agents skills

- [OpenMontage](https://varg.ai/how-to/skills/openmontage.md): Open-source agentic video studio: 12 pipelines (8 edit your footage), 100+ tools, ~140 skills. Run your agent in it.
- [video-use](https://varg.ai/how-to/skills/video-use.md): Drop raw takes in a folder, chat with your agent, get final.mp4: transcript-first cuts, grade, subtitles, overlays.
- [FireRed-OpenStoryline](https://varg.ai/how-to/skills/firered-openstoryline.md): Conversational editing agent: finds media, writes the storyline, beat-syncs music and refines the cut by chat.
- [ButterCut](https://varg.ai/how-to/skills/buttercut.md): Claude Code builds selects, scenes and rough cuts from your footage library and exports XML for FCP, Premiere, Resolve.
- [Agentic Video Editor (ave)](https://varg.ai/how-to/skills/agentic-video-editor.md): CLI where Gemini agents pick shots, trim, render with FFmpeg and score the result until a brief is met.
- [OpenChatCut](https://varg.ai/how-to/skills/openchatcut.md): Local-first chat video editor with a multi-track timeline that Codex and Claude Code can edit over MCP.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt