Signal Garden

设计资源DESIGN· MOTION

cutaway

Nyxera0x/cutaway

给Claude一张机械图,自动生成3D拆解动画视频。A Claude Code skill that turns a single reference image into a 3D object that disassembles itself, filmed at 60 fps with sound.

根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms
claude-code
已识别的要求Documented requirements
Local runtime
许可LICENSE
MIT

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

Featured on Signal Garden
徽章主题Badge theme

能力CAPABILITIES

它能帮你做成什么What it helps you do

  1. 01

    把一张图片变成能自动拆解的3D模型

  2. 02

    生成零件逐一分离又复原的60帧动画视频

  3. 03

    对照原图逐项检查3D重建的准确度

  4. 04

    先出静帧让你确认,再渲染完整影片

  5. 05

    用命令行直接运行三个现成的拆解示例

  1. 01

    Rebuild any object from one reference image as a 3D scene

  2. 02

    Watch every part separate and snap back together on film

  3. 03

    Check the build against the picture with a graded checklist

  4. 04

    Generate a 10-second or full 20-second film with sound

  5. 05

    Run three pre-built examples to see how it works

上手GET STARTED

怎么装How to install

SKILLS-CLI
npx skills add Nyxera0x/cutaway -g -a claude-code

选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY
未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME
是Yes
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
需要本地环境Needs a local runtime
05许可LICENSE
MITMIT
06阶段STAGE
持续活跃Active
创建于 06 NOV 2026Created 06 NOV 2026

静态扫描STATIC SCAN

  • 01控制浏览器Controls a browserreadme

    npm install && npx playwright install chromium
  • 02控制浏览器Controls a browserSKILL.md

    cd "$SKILL_DIR" && npm install && npx playwright install chromium

安装时会自动下载并运行 Chromium 浏览器,这意味着 Claude Code 能控制浏览器来渲染和录制画面。如果你不习惯让命令行工具自动安装浏览器,可以手动检查安装过程。The static scan flagged two medium-risk items for controlling a browser, which comes from using Playwright to capture the film. Review the code before running it if you are concerned about browser automation.

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

15 NOV 202615 NOV 2026

增长GROWTH

+91.3%+91.3%

206 → 394 stars · 7 个快照206 → 394 stars · 7 snapshots

状态STATUS

持续活跃Active

质量 A-Quality A-

你给 Claude 一张图片,它就能自动生成一个可拆解的 3D 模型,并拍成 60 帧的拆解视频,整个过程不需要你写一行代码。Built on top of an existing MIT-licensed runtime for frame capture and sound

每周一周刊Monday weekly digest

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

看第 1 期Read issue 1

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

订阅每周一周刊Subscribe to the Monday weekly digest
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
来源 URLSource URL
https://github.com/Nyxera0x/cutaway
原始数据哈希Raw data hash
fc2a3b16ba779c358ee37621d454b3d8
解析时间Parsed at
2026-11-22T00:10:08.020Z
最后一次验证Last verified
2026-11-21T22:14:32.240Z
增长测量时间Growth measured
2026-11-22T00:21:59.267Z
发现查询Discovery queries
focus:motion:code:threejs
分类来源Category source
rules
焦点Focus
motion (9)

依赖:Dependencies:@fontsource-variable/inter, @fontsource/jetbrains-mono, esbuild, playwright, three

完整解析证据 JSONFull parse evidence JSON
{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …# cutaway A Claude Code skill that turns one picture…"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 3,
      "ai-tools": 1,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 2,
      "productivity": 0
    },
    "primary": "design",
    "secondary": "motion"
  },
  "localRuntime": "ay sharp). Capture prints the GPU it got; a software renderer means the G",
  "skillMdTotal": 1,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 2,
    "design": 0,
    "browser": 1,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "1 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "SKILL.md"
  ],
  "skillMdFetched": 1
}