huashu-motion skill

A skill for Claude Code and Codex that turns one sentence into a product launch film, scores the music and edits a frame on click

  • 2,412 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The agent starts a local editor server, Chrome and FFmpeg and writes files into the film folder
  • Rendering opens agent-written code in Chrome, so review it before export
  • Voiceover and samples make the skill download models and files on command (about 55 MB and 325 MB)
All reasons and checks

alchaincyf/huashu-motion

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/huashu-motion

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 agent starts a local editor server, Chrome and FFmpeg and writes files into the film folder
  • Rendering opens agent-written code in Chrome, so review it before export
  • Voiceover and samples make the skill download models and files on command (about 55 MB and 325 MB)

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

What it does

huashu-motion teaches an agent to make launch films and motion graphics. You say "make a 30-second launch film for my product", the agent reads the product site, offers three directions with key frames, writes a beat sheet and opens an `om studio` editor in the browser. The film is a single `index.html` file: GSAP, Canvas, Three.js and SVG draw the frames, and no video generation model is called. The agent writes the music as ABC notation, and a program plays it with piano, string and drum samples. The `om samples build` command downloads the samples (about 55 MB); without it you hear a synthesizer. Sound effects hook to the line of code where an object lands. Voiceover uses a system voice or your own recording, aligned word by word. Editing works through comments. Press `C` in the editor, click the frame and write what to change. The agent receives the time, the scene and the element, looks at a zoomed frame and edits only that spot. Export is MP4, MOV with transparency, WebM, GIF or a share page with a player. The `om check` and `om qa` commands test the film before delivery.

Who it is for. For founders, marketers and developers who need a launch film or an animated data explainer without a video editor.

Good fit when

  • You need a 30-second release film: the agent reads your site, offers three directions and builds the film with music
  • You want an animated explainer from `data/funnel.csv` showing why conversion grew, with numbers in editable fields
  • A recorded video needs name tags, number cards and chapter cards exported with a transparent background for Premiere or other editors
  • You have a 16:9 film and need a vertical 1080×1920 version
  • You want an animated README header: `om share` prepares a GIF under 10 MB and the post text

Not a fit when

  • You need live footage or neural-generated video: the skill draws frames in code
  • You run Windows or Linux and cannot test yourself: the author verified macOS only
  • You want a fixed-grid template to fill in: the skill builds a film around the product

Example request

Use huashu-motion: make a 30-second launch film for my product, site example.com, and show three directions before you start

Limitations

  • Needs Node 22 or newer, Chrome, Chromium or Edge for rendering, and FFmpeg for export. The `om doctor` command shows what is missing.
  • Verified on macOS only. The Codex sandbox blocks local preview and the browser, so you approve those by hand.
  • Kokoro voiceover for Chinese needs uv, Python 3.12 and a model of about 325 MB, and word alignment needs `whisper-cli`.
  • On films longer than 4 seconds the skill adds a "Made with huashu-motion" caption at the end; ask the agent to turn it off.

How to disable. Delete the `huashu-motion` skill folder from your agent's skills directory (`~/.claude/skills/` or `~/.codex/skills/`). Finished films stay in your folders as plain `index.html` files.

FAQ

How do I install huashu-motion in Claude Code?

Run `npx skills add alchaincyf/huashu-motion -a claude-code`. You can also ask the agent: "install the huashu-motion skill from github.com/alchaincyf/huashu-motion and run the demo". The manual way is to clone the repository and link `skills/huashu-motion` into `~/.claude/skills/`.

Does the skill call paid models for music or video?

No. The agent writes the music as notes, a program plays it locally, and code draws the frames. The only cost is what you already pay your agent's model provider.

How do I change one spot in a finished film?

Open the `om studio` editor, press `C`, click the frame and describe the change. The agent receives the time, the scene and the element and edits only that. Every version is kept, and ⌘Z undoes a change.

Which export formats does huashu-motion have?

MP4, MOV with transparency, WebM, GIF and a share page with a player and the source. The `om share` command prepares a GIF under 10 MB and a `share.md` file with the post text.

What do I need to install first?

Node 22 or newer, Chrome, Chromium or Edge, and FFmpeg. `om doctor` shows what is missing. Voiceover and real instrument sounds need extra downloads.

Discussion

No questions or reviews yet.

Skills

A skill for promo films and kinetic type: idea and storyboard before the build, MP4 rendered through Chrome and ffmpeg, checked by six gates

SkillExtended access1.4KRepository stars

A skill for Cursor, Claude Code and Codex: from a product name or URL it builds a 4K promo with music, voice-over and checks

SkillExtended access452Repository stars

A kit for software product promo videos on HyperFrames: 101 themes, a transition atlas and a repetition check for storyboards

SkillExtended access254Repository stars

A Claude Code skill that builds a Remotion film of your product from its own components, tokens and logo, cut to music

SkillExtended access424Repository stars

A skill and Remotion pipeline: the agent studies your product and builds a demo video in React code, with no screen recording

SkillExtended access465Repository stars

A local video studio for your coding agent: describe a video in one sentence, the agent directs, your machine renders with no cloud

PluginExtended access321Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
huashu-motion (this card)no2,412
HyperFramesno79,556also builds video from HTML; huashu-motion adds notated music and click-on-frame editing
Remotion Agent Skillsno6,431teaches an agent Remotion on React, while huashu-motion works on a plain HTML page

README in short

The README shows sample films made by the skill itself and the prompts used to order them. It then gives three install routes, requirements, a table of typical requests, an explanation of how it works (the HTML file, direction rules, music, rendering) and a command list.

README badge

Original SKILL.md

---
name: huashu-motion
description: "Motion graphics, launch videos and explainers as editable code. A director picks the motion language for your product; you point at frames to change them. 动画、发布片、解说视频,指着画面改。"
metadata:
  author: "花叔"
  homepage: "https://github.com/alchaincyf"
  repository: "https://github.com/alchaincyf/huashu-motion"
  version: "0.3.1"
---

# huashu-motion

You are the director, designer and animator. The film is code: one composition (`index.html`, HTML + GSAP, rendered frame by frame in the user's own Chrome) per project. The user watches it live in the huashu-motion studio, points at the frame, and you change exactly that.

Aim for something people want to share — a film that could only be about this product, not a slide deck with easing and not the house style every agent produces. Working code is the starting line; the finished frames are the bar.

## The tool

```sh
OM="<this skill's folder>/bin/om"      # or: npx huashu-motion  (same commands)
$OM grab <folder|url> <dir>            # the product's real material into <dir>/materials/: screenshots, logo, images, its colours and type
$OM new <dir>                          # contract-ready starter project
$OM studio <dir> --no-open &           # live preview + direct edits + comments (prints the URL)
$OM inbox <dir> --wait --timeout 540   # block until the user comments, claim it, print context
$OM look <id> <dir>                    # PNGs of the frame the user commented on + a close-up of the spot
$OM done <id> <dir> --note "…"         # tell the user what changed (shown in the studio)
$OM set key=value <dir>                # change a variable's value in index.html
$OM sound <dir>                        # music + effects from the scenes, OM.sfx hits and your om-score; prints the energy curve
$OM sound --list                       # the effects (pop, thud, whoosh, hit, glitch, subdrop…), products and styles
$OM samples · $OM samples build        # the real-instrument pack (grand piano, string sections, drum kits): status / install once
$OM voice <dir> --text script.txt      # narration + word cues (OM.cue) + subtitles; or --audio <your recording>
$OM render <dir>                       # → <dir>/out/<name>-vN.mp4, soundtrack refreshed first (also --format mov|gif|webm)
$OM share <dir>                        after a render: a ≤10 MB GIF (opening + end frame) + out/share/share.md (post, README header)
$OM fonts · $OM fonts add "Noto Sans SC" <dir>   # bundled typefaces (CJK 500–900, serif, display), declared for you
$OM render <dir> --blur               # motion blur: up to 8 subframes averaged per frame, for fast UI and camera moves
$OM check <dir>                        # before rendering: scripts, files, motion rules, then sampled frames (cut-off / covered / low-contrast text)
$OM qa <dir> [--loop]                  # check the newest render: single-frame pops, dead time, cuts, motion curve, loop seam
$OM still <page.html|dir> --at 0,2.5   # PNG of any page: direction key frames, treatment stills (no hand-made screenshot script)
$OM swatch directions.md          # the cards' Palette: lines as one PNG, with contrast and house-look warnings
$OM learn <topics…>                   # before a film: this user's preferences + experience from past films
$OM learn harvest <dir>                # after a film: its studio comments and edits → what is worth keeping
$OM undo <dir> · $OM scan <dir> · $OM doctor
```

`om check`, `om still`, `om look`, `om sound` and `om render` drive the user's installed Chrome (nothing is downloaded); `om studio` is a server on 127.0.0.1. If your sandbox blocks starting a browser or a local server (e.g. Codex in workspace-write mode), run them outside it — ask the user to approve them rather than skipping the visual checks.

Report a problem

Foxx AIhuashu-motion
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.