Skip to content
appsgit

Video Scrub

Video Scrub is an agent skill (a SKILL.md file) from eternityspring/reelbench-skills. 把一条视频重建成「只有画面和声音」的干净文件——源片的元数据一概不搬： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流）， 隐私保证来自结构，不来自枚举。 难点不在容器 tag，在看不见的那几层：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进. It works with Claude Code and Codex and has 1,167 GitHub stars across a repository of 2 listed skills.

github.com/eternityspring/reelbench-skills/skills/video-scrub (opens in a new tab)

Data as of from the GitHub API; description from the skill's SKILL.md. Report an error

View on GitHub (opens in a new tab)

Add this skill

Claude

Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):

git clone --depth 1 https://github.com/eternityspring/reelbench-skills.git
cp -r reelbench-skills/skills/video-scrub ~/.claude/skills/video-scrub   # personal, or .claude/skills in a project

In the Claude apps, zip the video-scrub folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/eternityspring/reelbench-skills.git
cp -r reelbench-skills/skills/video-scrub .agents/skills/video-scrub   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/eternityspring/reelbench-skills.git
cp -r reelbench-skills/skills/video-scrub .cursor/skills/video-scrub   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

把一条视频重建成「只有画面和声音」的干净文件——源片的元数据一概不搬： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流）， 隐私保证来自结构，不来自枚举。 难点不在容器 tag，在看不见的那几层：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——ffprobe 一个都看不见。 五个藏身处逐一堵死，每一处都有实测。 默认 --mode copy：画面逐字节照搬（cmp 验证过），只重编音频，53 秒的片子 1.3 秒跑完； --mode encode 完整重编码，多杀掉码流域的东西。 验收不靠声称：把源片所有元数据字符串当「针」，在输出文件里做字节级扫描， 扎到一根就红。12 道门全部由脚本确定性检查。 零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 清元数据、去元数据、抹掉视频信息、视频隐私、去水印信息、 strip video…

More skills in eternityspring/reelbench-skills

2 skills are listed from this repository.

Similar skills

More docs & writing skills

All Docs & writing

FAQ

Video Scrub FAQ

Still curious? Email info@appsgit.com.

How do I install the Video Scrub skill?

Copy the video-scrub folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.

Is the Video Scrub skill free?

Yes. The repository is open source under the Apache-2.0 license. The skill mentions an API key or token for an external service, which may need its own account.

Is Video Scrub maintained?

The repository's most recent commit was on Oct 24, 2026. appsgit only lists skills from repositories with a commit in the last six months.