# Chatgpt Video Editing Setup

> Set up, repair, or verify the local AI short-video environment: video-use, FFmpeg, ElevenLabs credentials, and optional HyperFrames skills. Use whenever a user asks to install, configure, fix, reconnect, or check this editing environment. Do not use for Premiere or CapCut help, or to edit/transcribe media; hand those requests to the editing workflow after setup is verified.

- **Type:** Skill
- **Install:** `agentstack add skill-jaycheng1103-chatgpt-video-editing-skills-chatgpt-video-editing-setup`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Jaycheng1103](https://agentstack.voostack.com/s/jaycheng1103)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Jaycheng1103](https://github.com/Jaycheng1103)
- **Source:** https://github.com/Jaycheng1103/chatgpt-video-editing-skills/tree/main/skills/chatgpt-video-editing-setup

## Install

```sh
agentstack add skill-jaycheng1103-chatgpt-video-editing-skills-chatgpt-video-editing-setup
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ChatGPT Video Editing Setup

Prepare or repair the environment without starting creative work. The outcome is
an evidence-backed readiness report, not a transcript, upload, edit, preview, or
render.

## Read first

Read [the setup runbook](references/setup-runbook.md) for commands and install
choices. Read [security and verification](references/security-and-verification.md)
before handling credentials or declaring anything ready.

## Operating sequence

1. Inspect before changing anything: check the stable paths
   `~/Developer/video-use` and, only when requested, `~/Developer/hyperframes`.
   Recognize normal checkouts and linked worktrees with `git rev-parse`, then
   capture each repository's exact origin, branch or detached state, commit,
   and status. Also check available runtime tools and the active agent's Skills
   location. Do not print secrets.
2. Treat any existing path that is not a Git worktree as a hard stop. The only
   accepted origins are the exact official HTTPS URLs in the runbook. A missing
   or different origin and a dirty status are also hard stops: report the
   evidence, never rewrite the remote automatically, and do not pull, reset,
   overwrite, install dependencies, or register a Skill.
3. State the exact mutations needed, including clones, package installs, large
   downloads, or Skills-directory changes. Obtain explicit approval before any
   of them. Inspection and a no-cost local version check do not imply approval
   to mutate.
4. After approval, follow the runbook exactly and repeat the repository
   preflight immediately before dependency installation or Skill registration.
   Install/register the complete video-use repository so its helpers remain
   available. Treat HyperFrames as optional unless the user specifically needs
   HTML, CSS, or GSAP animation; when requested, require Node.js 22 or newer.
5. Configure ElevenLabs only through an existing environment variable or the
   protected `~/Developer/video-use/.env` path. Never echo, log, or commit a
   credential.
6. Verify with local, no-paid-work checks only. Run HyperFrames repository,
   Node, lockfile, and Core Skills checks only if HyperFrames was explicitly
   approved and installed; otherwise report it as not requested. Do not upload
   media, call transcription, create an edit directory, or edit/render video.
7. Report checked paths, approved mutations performed, evidence, versions or
   command outcomes, remaining gaps, and the explicit next action. Never claim
   readiness without successful evidence.

## Handoff boundary

Before any later first media upload to ElevenLabs, identify the source file,
state that it will be uploaded for transcription with ElevenLabs Scribe v2, note
that account quota or charges may apply, and obtain consent. Setup itself ends
before that point.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Jaycheng1103](https://github.com/Jaycheng1103)
- **Source:** [Jaycheng1103/chatgpt-video-editing-skills](https://github.com/Jaycheng1103/chatgpt-video-editing-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jaycheng1103-chatgpt-video-editing-skills-chatgpt-video-editing-setup
- Seller: https://agentstack.voostack.com/s/jaycheng1103
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.