Huashu Art Motion by Huashu — workflow skill for animation & motion graphics
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
Paintings that move: 35+ art styles and 9 explainer grammars as code, BPM-synced music, a QA subagent before delivery.
- Type: Workflow · Animation & motion graphics
- Slug:
huashu-art-motion - Status: beta
- Publisher: Huashu (alchaincyf) (community)
- License: MIT
- Source: https://github.com/alchaincyf/huashu-art-motion
- Works in: Claude Code, Codex
- Requires: uv (Python), ffmpeg, Playwright Chromium
- Cost: Free, MIT: renders locally; optional cloud TTS (Volcengine) is billed by that provider
- Adoption: 5,855 GitHub stars (GitHub, 2026-10-31)
What it does
A coding-agent skill that writes art styles as moving pictures: 53 style recipe cards (36 built, from cave painting, Egyptian murals, Van Gogh and Monet to Bauhaus, ink wash and 8-bit) each with scene code, motif motions and a signature transition, plus 9 explainer grammars (Kurzgesagt, Vox, whiteboard, 3Blue1Brown, storytime, kinetic type, keynote, finance charts) rendered as frame-exact clips from a JSON spec. It can break down and recreate a reference animation, synthesizes music on a BPM grid in code, and before delivery runs a QA script and an independent subagent that watches only the finished film; the delivery script blocks static, slide-like results. People come from image-model frames composited in code. The skill's docs are in Chinese (an English README exists): tell the agent to talk to you in English. About 5.9k GitHub stars; the remake prompt on X saved 3.7k times.
Use when
- an animated short or explainer in a named art style
- a narrated explainer segment in a known YouTube grammar
- a journey through famous paintings
- recreating a reference animation's motion and timing in code
Not for
- Readers who need English docs inside the skill: SKILL.md and most references are Chinese
Install
- Claude Code:
npx skills add alchaincyf/huashu-art-motion - Any agent, with the vargai CLI:
vargai install huashu-art-motion
Example output
https://s3.varg.ai/files/4325c578-378d-4c43-ae53-3cc3218df1ea/file_a9132ad7da71.mp4 — Monet's Japanese Bridge drawn in code: the character skips a stone and the pond ripples. The full 3.6 s loop, GIF re-encoded to MP4. (credit: Huashu (README), https://github.com/alchaincyf/huashu-art-motion#readme)
More animation & motion graphics skills
- Day in My Life: A 60–75 s hand-drawn ink film of your agent's day with you, built from local Claude Code history, scored for strings.
- p5 Paint Animation: Handwriting that writes itself, photos that paint themselves and clips repainted as living paintings, in p5.js code.
- Session Story: A 40–70 s watercolor film of a typical session with your agent, told in your real messages, with its own score.
- Remotion Markup: Write Remotion markup that animates well: timing, transitions, motion blur, effects, audio, fonts and 3D.
- Motion AI Kit: Write production-grade UI animation with Motion or CSS: best practices, docs search, springs, perf audits.
- Motion Design: Animate with intent: timing, easing, choreography and Disney principles for UI and motion graphics.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Any agent with a terminal:
curl -fsSL https://varg.ai/install | sh(Windows:irm https://varg.ai/install.ps1 | iex), thenvargai loginand every model is a command —vargai generate_video …,vargai estimate_cost …(https://varg.ai/how-to/cli/) - Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt