pyang5166 GitHub avatar

gbro-collage-info

pyang5166

gbro-collage-info is a Claude Code Agent Skill that turns voiceover script segments into 1080×1920 vertical halftone paper-collage info-graphic mp4 animations, rendered locally with HTML/CSS/GSAP via HyperFrames and no image-generation models.

Stars

22

7-day growth

No data

Forks

3

Open issues

0

License

MIT

Last updated

2026-08-01

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines a strict editorial visual style with a three-gate human-in-the-loop workflow, enforcing integrity rules like never fabricating UI screenshots or data, and it packages foley, motion grammar, and QA checks into a reusable local rendering pipeline.

Who it is for

  • Chinese-language video creators producing script-driven talking-head or explainer videos
  • Claude Code users who want AI-assisted motion-graphics production
  • Front-end developers or motion designers interested in programmatic HTML/CSS/GSAP animation
  • Teams seeking controllable, no-image-model alternatives for infographic animation

Use cases

  • Selecting animation-worthy passages from a voiceover script and producing a vertical mp4 with foley
  • Creating info-animations for numbers, processes, lists, comparisons, and result highlights
  • Reviewing static hero frames before committing to full animation via headless Chrome screenshots
  • Building local, self-contained HyperFrames animation projects with bundled assets and sound effects

Strengths

  • Three confirmation gates keep humans in control of segment choice, composition, and final delivery
  • Renders locally with HTML/CSS/GSAP, avoiding image-generation model costs and unpredictability
  • Hard style rules prevent fake UI and fabricated facts: placeholders stand in until real screenshots exist
  • Includes style system, motion grammar, setup script, QA checklist, and behavioral evals

Considerations

  • Requires Node ≥ 22, Chrome, and ffmpeg/ffprobe setup before use
  • Skill instructions and trigger phrases are written in Chinese, and layouts are tuned for CJK-density text
  • Deliberately rejects content types like UI walkthroughs and emotional monologues
  • The halftone paper-collage aesthetic is specific and may not fit every brand or video style

README quick start

安装

Description

半调纸拼贴风信息动画 Agent Skill · Halftone paper-collage info-graphic animations from voiceover scripts (HyperFrames, no image models)

Related repositories

Similar projects matched by category, topics, and programming language.

yetone
Featured
yetone GitHub avatar

kill-ai-slop

Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.

AI & Machine LearningAI Agents
805
MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
gnipbao
Featured
gnipbao GitHub avatar

story-to-handdrawn-video

A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.

AI & Machine LearningAI Agents
683