SkillFoxx

Video Illustrator skill

A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.

  • 53 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The skill runs rendering, ffmpeg and a Chromium browser on your machine.
  • Music is a paid OpenRouter call with your key and only with your permission.
All reasons and checks

axtonliu/video-illustratorAuthor:Axton Liu

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/video-illustrator

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The skill runs rendering, ffmpeg and a Chromium browser on your machine.
  • Music is a paid OpenRouter call with your key and only with your permission.

This is third-party code. Review the repository files before installing.

What it does

Video Illustrator turns your narration and real material, such as a book cover, screenshots and a logo, into a 20–60 second video. The material stays exactly as it is and the look comes from a style atlas: examples include cut paper, ink wash, pixel retro, particles, editorial tech and cinematic 3D. The output is an MP4 plus editable scene source, rendered on your machine. Since version 0.9 an episode mode makes a two to ten minute science or tech explainer. The skill picks an angle, builds a fact table with a cited source for every number on screen, writes an explanation plan and a segmented script and builds scenes in 3D or 2D. Sound effects are synthesized locally and music is an optional paid OpenRouter call.

Who it is for. Authors of courses, books and technical channels who want a promo or explainer video from their own voice and material.

Good fit when

  • A book launch needs a 30 second promo with the real cover.
  • A course is explained in a two minute video in a chalkboard or cut paper style.
  • A technical episode is built from a fact table where every number has a source.
  • One narration is rendered in several styles for comparison.

Not a fit when

  • You need a photorealistic video from a generative model.
  • Node.js and ffmpeg cannot be installed on the machine.
  • You expect automatic fact checking rather than source collection.

Example request

Make a 30 second video from my voice.wav narration and cover.png in the cut paper style.

Limitations

The skill is made for Claude Code with Opus 5.5 and other hosts are unverified. It needs Node.js 20 or newer, FFmpeg with ffprobe and Playwright Chromium. It is an early preview: one sentence will not always give a finished film, and longer narratives, fonts and audio can need extra work. Music through OpenRouter with the Lyria 3 model costs about $0.04 per 30 seconds and runs only with your permission, using your own `OPENROUTER_API_KEY`. It is code driven animation, not a video model.

How to disable. Delete the `video-illustrator` folder from `.claude/skills/`. Projects and videos the skill made are removed by hand.

FAQ

How do I install Video Illustrator?

Put the folder in `.claude/skills/video-illustrator/` and run `npm ci` and `npx playwright install chromium` inside it.

What does it need?

Node.js 20 or newer, FFmpeg and ffprobe on `PATH` and Playwright Chromium. A GPU is preferable for 3D, otherwise rendering runs in software and slower.

Do my materials go to an external service?

Rendering is local and nothing is sent to a hosted renderer. The exception is music through OpenRouter, which you enable manually.

What is episode mode?

A two to ten minute video: angle, research, a fact table with sources, a plan, a segmented script and 3D or 2D scenes.

Where can I see examples?

Each style in the README links to YouTube, and `showcase/SAMPLES.md` describes how each example was made.

Discussion

No questions or reviews yet.

Skills

A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix

SkillExtended access1.7K

A skill that makes video in pure code: narrated explainers and website promos in 35 visual styles, in 16:9 and 9:16.

SkillExtended access174

A skill that turns narration text into a 20-second chunky-pixel explainer at 1920×1080 with voice-over and an editable project.

SkillExtended access84

A Claude Code skill for short animated videos drawn in code: seven styles, story and storyboard sign-off, voice-over and an MP4 render

SkillExtended access1.8K

A skill that makes promo videos from code: direction, in-browser animation with motion blur, its own score and a 60 fps MP4

PluginExtended access78

The video-explainer skill turns a script into a vertical 9:16 explainer: narration, captions, Remotion and a pre-render review

SkillExtended access124

README in short

The repository shows one narration in six styles and describes video and episode modes. It is an early preview with best effort maintenance.

README badge

Original SKILL.md

---
name: video-illustrator
description: Turn the user's own voice and real assets (book or course covers, screenshots, logos) plus a chosen visual style into a 20–60 second cinematic promo or concept explainer, or turn a passage, article, idea or script into an animated illustration clip, or (explainer mode) make one passage of an existing narrated video visible as a mechanism insert in 16:9 and 9:16, or (episode mode) make a whole researched, narrated science or tech explainer with real footage. One system where every mode runs the same steps and picks its look from one style atlas (a bright 3D diagram by default for explainers and episodes). Use for 宣传片, 电影感短片, 配视频, 文字转动画, animated explanations, motion graphics, 讲解插入镜头, 机制示意, 整期科普片, 解释手法, or a short video illustration. Produces editable scene source and MP4 rendered locally; optional paid music generation. Not for editing an existing recorded video or managing a production timeline.
metadata:
  version: 0.9.0
  layer: workflow
  domains: [visual, video]
  maturity: experimental
  covers:
    - 电影感宣传片
    - 概念解说短片
    - 文字转动画
    - 20–60 秒 promo
    - 本人配音驱动时间线
    - 真实素材保真
    - 书封与课程封面
    - three.js 3D 渲染
    - Canvas/SVG 2D 动画
    - 视觉风格图谱
    - 概念装置 organizing device
    - keyframe 静帧检查
    - contact sheet 自检
    - 运动检查（静止、片尾停留、暗场）
    - 独立终检 review
    - 判例式审美准则
    - 风格 motion tokens
    - 克制预算
    - 转场词汇
    - 媒介手艺卡
    - 会做动作的主角
    - 制作感小字
    - 节拍网格
    - 旁白 onset 对齐
    - 程序化音效
    - 音效峰值对拍
    - 用户音效 inputs/sfx
    - Lyria 配乐生成
    - brand.json 片尾署名
    - 品牌包 brand.v2（色板、强调色规则、字号阶梯、motion、母题、禁用手法）
    - 品牌包校验与品牌样张
    - 用户默认品牌包（~/.config/video-illustrator/brand）与规则文档 rules_docs 现读
    - 卡片与标签不用 AI 默认样式（单边色条等）
    - 本地 MP4 渲染
    - 可编辑场景源码
    - 讲解模式（已有口播的一段做成机制示意）

Report a problem