Erduo B-roll Loop Engineering — workflow skill for AI editing agents
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/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://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
SRT-driven B-roll agent: a Director plans shots, Creators build them in HyperFrames or Remotion, a Reviewer checks.
- Type: Workflow · AI editing agents
- Slug:
erduo-broll-loop - Status: live
- Publisher: erduo1998-cell (community)
- License: MIT
- Source: https://github.com/erduo1998-cell/erduo-broll-loop-engineering
- Works in: Codex, Claude Code
- Requires: Node.js
- Cost: Free/open source
- Adoption: 232 GitHub stars (GitHub, 2026-10-27)
What it does
A multi-role skill that takes a full source SRT and a design brief and produces editable B-roll for a talking-head video. An independent Director sets the visual world and shot cards anchored to meaning (not one shot per subtitle line), Creators build continuous chapters in fresh contexts, the parent renders and an independent Reviewer looks at the actual frames and sends fixes back. Output is per-shot files, editable source and a full preview.
Use when
- add motion B-roll over a talking-head video from its SRT
- keep shots tied to the spoken timeline
- get editable HyperFrames/Remotion source, not just an MP4
Install
- Claude Code:
git clone https://github.com/erduo1998-cell/erduo-broll-loop-engineering.git
Example output
https://s3.varg.ai/how-to/previews/488f9df1ba1d/erduo-broll-loop.mp4 — Image from the project README (credit: erduo1998-cell (README), https://raw.githubusercontent.com/erduo1998-cell/erduo-broll-loop-engineering/main/docs/images/demos/homepage-showcase.gif)
More AI editing agents skills
- OpenMontage: Open-source agentic video studio: 12 pipelines (8 edit your footage), 100+ tools, ~140 skills. Run your agent in it.
- video-use: Drop raw takes in a folder, chat with your agent, get final.mp4: transcript-first cuts, grade, subtitles, overlays.
- FireRed-OpenStoryline: Conversational editing agent: finds media, writes the storyline, beat-syncs music and refines the cut by chat.
- ButterCut: Claude Code builds selects, scenes and rough cuts from your footage library and exports XML for FCP, Premiere, Resolve.
- Agentic Video Editor (ave): CLI where Gemini agents pick shots, trim, render with FFmpeg and score the result until a brief is met.
- OpenChatCut: 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