# Bggg Tiktok Readvideo

把 TikTok、Reels、YouTube Shorts、UGC 广告、本地 MP4/MOV/WebM 等视频拆成 Codex 可读的视频上下文。 当用户要求 Codex...

- Repository: https://github.com/binggandata/bggg-skills (612 stars)
- Category: Media
- License: MIT
- Last updated: 2026-08-13
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add binggandata/bggg-skills --skill bggg-tiktok-readvideo -g -a claude-code -y`
Codex: `npx skills add binggandata/bggg-skills --skill bggg-tiktok-readvideo -g -a codex -y`
Cursor: `npx skills add binggandata/bggg-skills --skill bggg-tiktok-readvideo -g -a cursor -y`
Gemini CLI: `npx skills add binggandata/bggg-skills --skill bggg-tiktok-readvideo -g -a gemini-cli -y`

## Description

把 TikTok、Reels、YouTube Shorts、UGC 广告、本地 MP4/MOV/WebM 等视频拆成 Codex 可读的视频上下文。 当用户要求 Codex 看懂视频、读视频、分析视频、总结视频、找 hook、找爆点、提取字幕、 语音转文字、ASR、批量转写 TikTok 视频或音频、 生成视频 timeline、抽关键帧、做 contact sheet、分析口播/画面/节奏、制定 TikTok 9:16 剪辑方案、 或把原始视频素材变成 edit_plan.json 并用 FFmpeg 渲染短视频时，应该使用此 skill。 本 skill 独立内置 ffprobe/ffmpeg/whisper.cpp/tesseract 可选流程，不依赖其他 BGGG skills。

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# BGGG TikTok ReadVideo

这个 skill 的原则很简单：不要让 Codex 直接“看 mp4”。先把视频拆成可读、可搜索、可执行的上下文，再让 Codex 做判断、剪辑规划和渲染。

核心脚本：

```bash
python3 bggg-tiktok-readvideo/scripts/analyze_video.py "/path/to/input.mp4"
```

只需要转写音轨时使用独立转写脚本：

```bash
python3 bggg-tiktok-readvideo/scripts/transcribe_video.py "/path/to/video-or-folder" --recursive --srt
```

脚本会创建：

```text
bggg-tiktok-readvideo/projects/YYYYMMDD_slug/
├── raw/input.mp4
├── analysis/
│   ├── metadata.json
│   ├── transcript.txt
│   ├── transcript.srt
│   ├── scenes.json
│   ├── timeline.md
│   ├── contact_sheet.jpg
│   ├── keyframes/
│   ├── audio_events.json
│   ├── ocr.json
│   └── analysis_manifest.json
└── output/
    └── edit_plan.template.json
```

## Default Workflow

1. Run `scripts/analyze_video.py` before making any claim about the video content.
2. If the user only asks for transcription/ASR, run `scripts/transcribe_video.py` instead of the full visual analysis pipeline.
3. Read `analysis/timeline.md`, `analysis/scenes.json`, `analysis/transcript.srt`, `analysis/audio_events.json`, and `analysis/ocr.json`.
4. Inspect `analysis/contact_sheet.jpg` as the visual overview. Use individual `analysis/keyframes/frame_XXXX.jpg` when a scene needs closer visual reading.
5. If the user asks for TikTok editing, write `output/edit_plan.json` before rendering.
6. Render with `scripts/render_tiktok.py` only after the edit plan exists.

Do not infer content from the filename, title, or folder name alone. The timeline and contact sheet are the source of truth.

## Analyze Commands

Basic local analysis:

```bash
python3 bggg-tiktok-readvideo/scripts/analyze_video.py "/path/to/video.mp4"
```

Give the run a stable project name:

```bash
python3 bggg-tiktok-readvideo/scripts/analyze_video.py "/path/to/video.mp4" \
  --slug product_qc_ugc
```

Faster visual-only pass:

```bash
python3 bggg-tiktok-readvideo/scripts/analyze_video.py "/path/to/video.mp4" \
  --no-transcribe --max-frames 24
```

Use a specific whisper.cpp model:

The rest: https://github.com/binggandata/bggg-skills/blob/HEAD/bggg-tiktok-readvideo/SKILL.md