AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Vision / Multimodal/
huashu-motion
huashu-motion logo

huashu-motion

Active·★ 2.9k·MIT·Updated 2026-11-16

huashu-motion by alchaincyf is an open-source agent skill (MIT license) engineered for Claude Code, Codex, WorkBuddy, and other modern agent runtimes. Operating on the premise of 'one-prompt commercial launch films', it empowers AI agents to autonomously conceptualize, script, score, and animate full-motion promotional videos.

The workflow establishes a disciplined creative pipeline: the agent studies your project documentation, proposes three creative storyboard concepts, drafts the complete narrative script, writes musical scores using ABC notation to synchronize beat drops to visual scene transitions, and launches a local browser editor. The standout feature is its 'point-to-edit' interaction: users press 'C', click any visual element on the canvas, and dictate precise revisions. The agent receives exact timecode and source coordinates, surgically modifying only that component while preserving the surrounding timeline.

Delivering resolution-independent vector animations rendered via web technologies, huashu-motion is an invaluable asset for bootstrapped founders and indie makers needing promotional reels. However, the system is designed around 2D motion graphics, typography, and UI demonstrations; it does not render photorealistic 3D environments, and exporting final MP4 videos requires a local Node.js canvas capture environment.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
MIT
Latest release
v0.4.0 · 2026-11-09
Last commit
2026-11-10
Contributors
1
Forks
266
Open issues and PRs
3
First published
2026-10-18

Source: GitHub, npm and PyPI public APIs.

#agent-skills#animation#claude-code#claude-code-skills#claude-skills#codex#dev-tooling#explainer-video
$ Install
$ npx skills add alchaincyf/huashu-motion
↗ Visit site★ GitHub
01

Features

01Frame comments retain time, scene and element context.
02Generates local scores and synchronized sound effects.
03Exports video, transparent formats and shareable HTML.
02

Why choose it

+Unique 'point-to-edit' visual canvas interface allows localized, surgical code revisions pinned to timecodes and elements.
+Score-first production pipeline uses ABC musical notation to guarantee seamless synchronization between cuts and beats.
+Proposes 3 creative concepts before animating, ensuring the final visual direction aligns with product branding.
+Produces resolution-independent, ultra-lightweight vector animations rendered via standard web primitives.
03

Trade-offs

!Focused on 2D motion graphics, typography, and UI demos; cannot render complex 3D photorealistic CGI scenes.
!Exporting final high-definition MP4/WebM video requires local Node.js and browser canvas capture runtimes.
!Generating multiple video iterations can consume substantial LLM tokens during script and styling cycles.
!Complex musical scores in ABC notation require the host LLM to maintain consistent musical composition rules.
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-10
Commits, last 90 days
17
Releases, last 90 days
6
Latest release
v0.4.0 (2026-11-09)
Open issues
3
Recent issues with at least one comment
0/3
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 15, 0, 0, 2

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #4 Windows: temp-dir cleanup EPERM in om render hides the real error (CDP timeout with default workers)0 comments · 2026-10-30
  • #3 Windows 11: `om render` intermittently exits with a zero-byte MP4, including with Microsoft Edge0 comments · 2026-10-23

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

macos
README reports testing on macOS only
Verified via docs
nodejs
Node.js 22+, Chrome-compatible browser and FFmpeg
Verified via docs
06

Quick start

1
$ npx skills add alchaincyf/huashu-motion
07

Use cases

↳Produce a product launch animation.
↳Turn data into a narrated visual explanation.
↳Revise a specific frame through editor comments.
08

Alternatives

⚡Top VS:
VShuashu-design★29.7k→VSmodlens★5.0k→VSdrama-skills★4.4k→VSdarwin-skill★7.0k→
huashu-design logo
huashu-design★ 29.7k
Huashu Design 3.0 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent
VSCompare→
video-shotcraft logo
video-shotcraft★ 21.0k
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
modlens logo
modlens★ 5.0k
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
VSCompare→
drama-skills logo
drama-skills★ 4.4k
AI 短剧与漫剧制作 skill 合集:小说改剧本、角色设定三视图、分镜脚本、生图/生视频提示词与成片审片,适配 Claude Code / Codex 等 | Open-source agent skills for AI short dramas & motion comics
VSCompare→
darwin-skill logo
darwin-skill★ 7.0k
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
VSCompare→
brag logo
brag★ 21.8k
You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.
VSCompare→
rea-video logo
rea-video★ 10.3k
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。
awesome-short-drama-skills logo
awesome-short-drama-skills★ 2.5k
AI 短剧 · 漫剧 Skill(技能包)精选:剧本、改编、分镜、Seedance / 可灵 / MiniMax 视频提示词,千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for AI short drama, micro drama / microdrama, vertical drama and manju (AI comic drama): screenwriting, storyboards, Seedance / Kling / MiniMax video prompts
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
alchaincyf /
huashu-motion
↗

Agent skill for generating commercial product launch videos with interactive point-and-click visual canvas editing

2.9k266MIT
Last commit2d ago
StatusActive
CategoryVision / Multimodal
Contributors1
Latest releasev0.4.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.