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
- 621 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs the terminal and FFmpeg and works with files on disk
- With consent uploads footage to ElevenLabs, which spends credits
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/chatgpt-skillsDetects 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 the terminal and FFmpeg and works with files on disk
- With consent uploads footage to ElevenLabs, which spends credits
This is third-party code. Review the repository files before installing.
What it does
The pair of skills splits the work into environment setup and the edit itself. The first skill checks, installs and repairs the needed tools: video-use, FFmpeg, ffprobe, the subtitle font, an ElevenLabs key and optionally HyperFrames. The second takes your supplied video through eight steps: source check, verbatim transcription, content review, edit strategy, rough cut, color and subtitles, mixdown with a full preview, final QA and export. The source is never overwritten, every new artifact goes into a sibling edit folder. Before any cloud upload or spend, the skill asks for consent.
Who it is for. For creators, social media specialists and editors who cut vertical clips from their own footage through an agent.
Good fit when
- You need to build a vertical clip from your own video with subtitles
- You need to set up and verify the editing environment first
- You want editing with explicit steps and a check before the final
Not a fit when
- You need generic Premiere Pro or CapCut help
- You have no source file and want video generated from scratch
Example request
First check my editing environment with the setup skill, install nothing without my consentLimitations
It needs an agent with local file and terminal access, plus Git, Python, uv, FFmpeg and the full video-use repository. Full transcription precision goes through ElevenLabs Scribe v2, which is cloud, a key and possible spend, and its access from some regions is not guaranteed. A local Whisper fallback exists with lower timestamp precision. The documentation is in traditional Chinese.
How to disable. Remove the skills: npx skills remove chatgpt-video-editing-setup chatgpt-short-video-editor.
FAQ
Why two skills?
One only checks and sets up the environment and never touches the footage, the other cuts the video and never installs tools silently. Setup and editing stay out of each other's way.
Must I upload footage to the cloud?
No. Full precision uses ElevenLabs, but you can explicitly choose local Whisper with lower timestamp precision and extra edge checks.
Discussion
No questions or reviews yet.
Related
SkillsAn agent edits short talking-head videos: transcript, subtitles, B-roll and export for Xiaohongshu, Douyin and WeChat Channels
Free Claude Code skills for short-form video: scripts, local editing, translation with a cloned voice and publishing.
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
A video editing skill for Claude Code and Codex: the agent cuts pauses and filler words, grades color, burns subtitles and adds animated overlays
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
video-production-skill takes an agent from script to video: slides, speech-verified narration, subtitles and a cover.
README in short
The README describes a pair of traditional-Chinese skills for agents with file and terminal access. The setup skill checks and installs video-use, FFmpeg, ffprobe, the subtitle font and an ElevenLabs key, doing nothing silently. The editing skill takes a vertical clip through eight steps from source check to final export, protects the original and collects results in an edit folder. It stresses consent before uploads and spend, verification against real output, and that previews and commands are not a finished result. Install is through the open skills CLI.
README badge
Original SKILL.md
--- name: chatgpt-short-video-editor description: "Edit a user-supplied video into a vertical Reel, Short, TikTok, video diary short, or an approved eight-step AI short-video workflow. Use when the user provides or points to media and asks to transcribe, cut, subtitle, preview, or export a vertical short. Do not use for environment-only setup or generic Premiere Pro or CapCut help." --- # ChatGPT Short-video Editor Create a safe, evidence-backed vertical short from user-provided media. This Skill starts only when a source file or clear source location is available. ## Boundary and prerequisites 1. Inspect the source with ffprobe; never overwrite, move, rename, or delete it. Put every new artifact beside the source in <source-directory>/edit/. 2. Check that the installed video-use workflow, FFmpeg, ffprobe, and ElevenLabs Scribe v2 are available for the documented full-precision path. Do not install, clone, update, or repair anything silently. 3. Before the first upload of a source file to ElevenLabs, name the file, say it is for ElevenLabs Scribe v2 transcription, mention possible quota or cost, and wait for explicit consent.