Video Editing Skill
An agent edits short talking-head videos: transcript, subtitles, B-roll and export for Xiaohongshu, Douyin and WeChat Channels
- 207 ★ on the repository
- Last commit
Extended access
Why this level
- Runs ffmpeg and dozens of Python scripts, reads source videos and writes working copies and final files
- Setup pulls dependencies through brew and pip, and the optional YOLO is a separate install
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/video-editing-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs ffmpeg and dozens of Python scripts, reads source videos and writes working copies and final files
- Setup pulls dependencies through brew and pip, and the optional YOLO is a separate install
This is third-party code. Review the repository files before installing.
What it does
The skill for Codex and OpenClaw takes a short video from raw files to a publishing package. It targets videos where a person talks to camera: tutorials, interviews, podcast clips, screen recordings with a face cam. The agent inspects the material folder, transcribes speech with word timestamps, removes slips and pauses, builds a storyboard, adds B-roll, chapters, stickers and music, burns subtitles and renders the result in one ffmpeg pass. The defaults are tuned for Chinese social platforms: Xiaohongshu, Douyin and WeChat Channels get fitting aspect ratios, durations and a wording check before release. Dozens of separate Python scripts sit alongside: environment checks, frame-rate conforming, black-edge trimming, joining clips of different formats, stabilization, LUT color grading, speed ramps, loudness and encode-quality checks. Every step writes a verifiable file with source checksums, and at the end the agent delivers a title, a description and tags.
Who it is for. Creators of short videos for Chinese platforms who record a talking head or a screen and want an agent to handle the edit.
Good fit when
- A talking-to-camera recording has to become a vertical video with subtitles, chapters and B-roll
- Phone footage has a variable frame rate and has to be conformed to a constant one before editing
- A long podcast is cut into short vertical clips with subtitles for each sentence
- Before publishing to Xiaohongshu, Douyin and WeChat Channels you want a wording check and an export for each platform
Not a fit when
- The edit is cinematic, a music video or a video with fine keyframe control: the README names these as a poor fit
- You want a timeline editor with a mouse: the agent works with scripts and ffmpeg commands
- The video targets other platforms: presets and checks are tuned for Chinese ones
- The machine has no ffmpeg and no Python 3.10 or newer
Example request
Take the folder with the recording and B-roll, transcribe the speech, cut the pauses and build a vertical clip with subtitles for XiaohongshuLimitations
- The skill is tuned for Chinese platforms and the Chinese language: presets, word checks and CJK-heavy subtitles target them, and the README is in Chinese.
- It needs ffmpeg, Python 3.10 or newer and a Whisper engine. For Apple Silicon the README advises `mlx-whisper`; other platforms install their own engine from a table.
- The repository has no license file, so reuse terms are not stated.
- There are dozens of scripts and a newcomer may not know where to start: the README says to run `runtime_preflight.py` first.
How to disable. Remove the repository folder from the agent's skills directory. ffmpeg and mlx-whisper stay on the system and are removed with their own package manager. Edit results sit in project folders next to the sources.
FAQ
Which platforms is Video Editing Skill built for?
Xiaohongshu (RED), Douyin and WeChat Channels: aspect ratios, durations and wording-check rules are built into the export. The README lists no presets for other platforms.
What do I install first?
ffmpeg, Python 3.10 or newer and a Whisper engine. On an Apple Silicon Mac the README suggests `brew install ffmpeg` and `pip install mlx-whisper Pillow`. Then `scripts/runtime_preflight.py` reports which commands, codecs and ffmpeg filters are missing.
How do I confirm the scripts work?
Run `pytest tests/` in the repository folder. According to the README the suite has 1259 tests and takes about 32 seconds.
Is it suitable for cinematic editing?
No. The README calls film-style cuts, music videos and videos with fine keyframe control a poor fit.
What does the agent deliver at the end?
The finished video, subtitle files, proof files for each step and a publishing package with a title, a description and tags.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code skill that downloads a YouTube video, splits it into semantic chapters, cuts chosen clips, translates subtitles and burns bilingual ones in
ChatGPT short-video editing skills
ChatGPT 剪短影音 Skills
Two agent skills: set up the editing environment and build a vertical short video in eight verified steps
Six skills that let the agent turn video into a short Chinese narration recap, locally via ffmpeg
A skill that automates JianYing editing: from a description the agent writes copy, adds voice, subtitles, music and effects.
A video editing skill for Claude Code and Codex: the agent cuts pauses and filler words, grades color, burns subtitles and adds animated overlays
ffmpeg-skill — a skill and MCP server: an agent cuts and joins video, fixes audio, adds captions and exports for TikTok and Reels with local FFmpeg
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Video Editing Skill (this card) | no | 207 | |
| video-use | no | 30,591 | an editing skill for Claude Code and Codex that cuts pauses and color-grades; this one targets Xiaohongshu, Douyin and Channels with verifiable steps |
| Video Editor Skills | no | 416 | editing skills that remember the author's notes, with no ready publishing package for Chinese platforms |
README in short
The README starts with a list of scenarios, from a voice and screen recording to a ready publishing package. Then come a diagram of dozens of steps with script names, a section on optional object detection with YOLO, a 60-second quick start and tables of dependencies and Whisper engines by platform. Each script gets a one-line description: what it does, which checks it passes and which proof file it writes.
README badge
Original SKILL.md
---
name: video-editing
description: "Xiaohongshu/RED-tuned short-form video workflow for voice-over, talking-head, tutorials, interviews, podcasts, screen recordings, chroma key, B-roll, captions, and generated assets. Covers source ingest and conformance, hard and ping-pong loops, edit routing and runtime profiles, transcription and semantic review, multi-take and multicam sync/speaker switching, stabilization/dead-air cleanup, highlights/shorts, story/source/authorization gates, B-roll and generated-asset planning/review, storyboard animatics and shot handoffs, audio design/mix/loudness, captions, color/speed/J-L cuts, local upscale/interpolation review, reversible revisions, render/QA, multi-platform and size exports, publish packages, NLE handoff, and Remotion."
metadata: { "openclaw": { "emoji": "🎬", "os": ["darwin", "linux", "win32"], "requires": { "bins": ["ffmpeg", "python3"] }, "install": [{ "id": "ffmpeg-brew", "kind": "brew", "formula": "ffmpeg", "bins": ["ffmpeg"], "label": "Install FFmpeg (brew)" }] } }
---
# Video Editing Skill — 视频剪辑技能（V3）
适配 **小红书 / 抖音 / 微信视频号** 三大主流平台。一条 **从素材导入 → 口播 → 重组故事 → 平台守门 → 自动丰富 → 渲染 → 三平台导出 → 标题文案** 的端到端流水线，按各平台的算法、比例、时长、审核规则调过参——不只是剪辑工具。
## V3 完整流水线（一图看懂）
```
口播音频 + 无声素材
│
├─→ project_bootstrap.py 原始素材目录 → source inventory / project.md
├─→ edit_brief_plan.py 用户一句话需求 → 本地脚本 runbook / gates
├─→ runtime_preflight.py workflow profile → FFmpeg/Node 命令、编码器、filters / live gate
├─→ interlace_conform.py 交错/telecine 采样 → progressive 工作副本 / 全长 A/B gate
├─→ frame_rate_conform.py 手机/录屏 VFR → 全量 PTS 检测 / CFR 工作副本 / live gate
├─→ black_edge_trim.py 首尾黑场 + 静音覆盖 → CFR 工作副本 / 原片边界 proof + live gate
├─→ program_breaks.py 内部黑场与全音轨静音重叠 → 只读分段候选 / 复核时间点
├─→ border_crop.py 画面内持续黑边 → 逐时点 cropdetect 证据 / 保守裁切建议
├─→ motion_center.py 局部像素运动中心 → 只读构图复核时间点
├─→ loop_fill.py 短片 → 次数/固定时长 hard repeat / 真实接缝 proof + 完整审片 gate
├─→ ping_pong_loop.py 短动作 → 端帧去重正放/倒放 / 折返+循环双 proof / live gate
├─→ clip_assembly.py 多源片段 → 单次画布/CFR/SAR/音频归一 / 全接缝 proof + live gate
├─→ edit_style_profile.py 个人/品牌创意方向、节奏与渲染/文案默认值 → 可移植 profile
├─→ production_authorization.py
│ 确切素材/动作/provider/权利依据 → 显式授权 + live gate
├─→ transcribe.py 转写 + 词级时间戳 + 口误标记
├─→ transcript_silence_qa.py 原始转写 vs 实测静音 → 幻觉疑点供回听
├─→ transcript_lookup.py 原话检索 / 时间窗口读取 → 少量带源时间码的结果
├─→ visual_transcript_index.py
│ 现有关键帧 + 附近原话 → 带源哈希的 JSON/Markdown 复核索引
├─→ semantic_transcript_review.py
│ 全篇前后文审校包 / 最小补丁验证 / 人工 choices gate
├─→ transcript_review.py 本地同步媒体 HTML 校稿 / CPS 提示 / review.txt 回写
├─→ takes_pack.py 多 take / Scribe transcript → phrase-level 阅读视图
│ speaker / audio_event 编辑节拍