Video Recap Skills — 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.mdto its path. Before generating anything, show the person the options on the how-to page.
Seven skills that cut one or more videos into a narrated recap: scene detection, ASR, VLM, script, TTS, ffmpeg.
- Type: Workflow · AI editing agents
- Slug:
video-recap-skills - Status: live
- Publisher: Zenstory (community)
- License: MIT
- Source: https://github.com/zenstory-ai/video-recap-skills
- Works in: Claude Code, Codex
- Requires: Python 3.10+, ffmpeg, Xiaomi MiMo API key
- Cost: Free/open source
- Adoption: 592 GitHub stars (GitHub, 2026-10-27)
What it does
Claude Code and Codex skills from Zenstory that turn episodes of a show or drama into a Chinese narration recap (jieshuo). They detect scenes, transcribe, understand frames with a VLM, write and voice the script, assemble with ffmpeg and can export a JianYing draft for further edits. Remote calls go through one Xiaomi MiMo key; locally only ffmpeg is needed.
Use when
- make a narrated recap of a series or film
- pick and reorder scenes from several episodes
- finish the recap in JianYing
Install
- Claude Code:
/plugin marketplace add zenstory-ai/video-recap-skills then /plugin install video-recap-skills@video-recap
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