LeaderAI Media Toolkit skill
Four skills for short-video creators: a spoken script writer, a talking-head editor, an explainer animator and a self-updater.
- 173 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Scripts run FFmpeg and Node.js on local files and download fonts.
Install
- Works in
Manual install
/plugin marketplace add AzenYes/leaderai-media-toolkitThe first Claude Code install command; the second step is `/plugin install leaderai-media-toolkit@leaderai`.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Scripts run FFmpeg and Node.js on local files and download fonts.
This is third-party code. Review the repository files before installing.
What it does
The pack contains `lead-media-script`, `lead-media-edit`, `lead-knowledge-animation` and `leaderai-toolkit-update`. The first writes a spoken script and saves two files: plain narration text and a recording plan with titles, opening variants and facts to verify. The second edits recorded video with FFmpeg, Whisper and Remotion: it removes slips, adds single-line subtitles and animated inserts in vertical and horizontal formats. The third turns a topic into a voiceless animation with no source footage, subtitles and two 4K covers. The fourth updates the installed pack to the latest release.
Who it is for. Short-video creators on Chinese-language platforms and YouTube who script, edit and make explainer clips with an agent.
Good fit when
- You have a topic but no script for a 60–90 second clip.
- Recorded video must be cleaned of slips and given subtitles.
- A channel needs an explainer animation with no voice recording or source footage.
- The same clip ships in vertical and horizontal formats.
Not a fit when
- The task is not video: audio podcasts, articles, posts.
- The agent cannot run commands or read local files; editing needs both.
- You need Russian speech or Russian subtitles; the pack is built around Chinese speech.
Example request
Write a 90 second script on why beginners stall at the intro and save the clean text and the recording plan as separate files.Limitations
Editing and animation need Python 3.10, FFmpeg with `libass`, Node.js 22 and Whisper-based speech recognition tuned for Chinese. IBM Plex Sans SC and Noto Serif SC fonts download on first run, about 220 MB for animation and 40 MB for editing. Music is not shipped. Documentation and skill names are Chinese. Installation through `npx skills add` is not supported because of the Chinese names.
How to disable. In Claude Code run `/plugin uninstall leaderai-media-toolkit@leaderai`. For a manual install delete the copied folders from the skills directory. Downloaded fonts sit in the skill `assets/fonts/` folder.
FAQ
How do I install it in Claude Code?
Through the plugin marketplace: `/plugin marketplace add AzenYes/leaderai-media-toolkit`, then `/plugin install leaderai-media-toolkit@leaderai`. Restart Claude Code afterwards.
How do I install it in Codex?
Copy the needed folders from `skills/` into the Codex skills directory, keeping English names and the nested `references/`, `scripts/`, `assets/`. The Chinese display name comes from `agents/openai.yaml`.
How do editing and animation differ?
Editing processes an already recorded video of a person. Animation is built from scratch from a topic with no filming or voiceover.
Does the environment need setup?
Not for scripts. Editing and animation need Python 3.10, FFmpeg, Node.js 22 and several Python packages listed in the README.
How do I update the pack?
Ask the agent to update the toolkit or call the `leaderai-toolkit-update` skill: it detects how it was installed and reports version changes.
Discussion
No questions or reviews yet.
Related
Skillsvideo-production-skill takes an agent from script to video: slides, speech-verified narration, subtitles and a cover.
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
The video-explainer skill turns a script into a vertical 9:16 explainer: narration, captions, Remotion and a pre-render review
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
Seven AI video skills: promo film planning, scene and fight prompts, acting direction and generation task reliability checks.
README in short
Each skill sits in its own folder with its own version and can be installed alone or together. At review time the main branch corresponds to version 1.7.1.