zenstory-ai

video-recap-skills

Recently maintained

Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut draft export (剪映草稿导出). Local ffmpeg + one MiMo key, no GPU. | 用 Claude Code skills 把视频做成中文解说成片,可选一键导出可编辑剪映草稿。

Stars
602

Community interest

Forks
110

Community forks

7-day growth
+10

Observed snapshot change

Language
Python

Repository metadata

Star history & growth

Observed snapshots only. Missing observations are not invented.

603 ★49 observations
2026-08-102026-11-03
Inspect recent observations
DateStars
2026-10-05550
2026-10-06554
2026-10-07555
2026-10-08559
2026-10-09561
2026-10-10562
2026-10-11564
2026-10-12567
2026-10-13570
2026-10-14575
2026-10-15575
2026-10-16578
2026-10-17579
2026-10-18581
2026-10-19581
2026-10-20582
2026-10-21586
2026-10-22588
2026-10-23589
2026-10-24589
2026-10-25591
2026-10-26592
2026-10-27593
2026-10-28595
2026-10-29595
2026-10-30598
2026-10-31599
2026-11-01601
2026-11-02603
2026-11-03602

Get the source & start here

Cloning downloads source; follow official setup and dependency instructions.

git clone https://github.com/zenstory-ai/video-recap-skills.git
READMEgithub.dev

About this project

What is video-recap-skills?

Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut draft export (剪映草稿导出). Local ffmpeg + one MiMo key, no GPU. | 用 Claude Code skills 把视频做成中文解说成片,可选一键导出可编辑剪映草稿。

How do I get started?

Clone with git clone https://github.com/zenstory-ai/video-recap-skills.git. Cloning is not a complete installation; follow the official README for dependencies, hosts and usage.

Can I use it commercially?

Current license information: MIT. Review the original terms, dependencies and your intended use.

What do maintenance and growth indicate?

Current status: Recently maintained. Activity is not a security audit. Growth uses collected snapshots; missing baselines are not estimated.