Signal Garden

设计资源DESIGN· FIGMA

figwright

awdr74100/figwright

一个免费的双向工具,让AI把Figma设计变成代码,也能把代码推回画布。Figwright is a free, two-way bridge between Figma designs and code, letting you generate code from designs and push code back to the canvas.

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
未确认Not confirmed
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 Figma 设计图转成能用的代码

  2. 02

    把写好的代码推回 Figma 画布

  3. 03

    自动更新 Figma 插件类型定义

  4. 04

    升级 通用接法 相关依赖并检查兼容性

  1. 01

    Turn a Figma design into ready-to-use code

  2. 02

    Push code changes back into the Figma canvas

  3. 03

    Generate code that matches your project's tech stack

  4. 04

    Work with AI coding tools to speed up development

  5. 05

    Keep design and code in sync automatically

上手GET STARTED

怎么装How to install

MCP config
{
  "mcpServers": {
    "figwright": {
      "command": "npx",
      "args": ["-y", "@figwright/mcp@latest"]
    }
  }
}

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
未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
一键安装One-click install
05许可LICENSE
MITMIT
06阶段STAGE
持续活跃Active
创建于 18 JUN 2026Created 18 JUN 2026

静态扫描STATIC SCAN

  • 01控制浏览器Controls a browserreadme

    `figwright` follows the **_-wright_** tradition, an old English word for a maker or craftsman: a **playwright** writes plays, a **shipwright
  • 02安装时执行脚本Runs a script during installpackage.json

    postinstall: node scripts/sync-skills.mjs

扫描发现两个中等风险:一是项目会控制浏览器(来自名字里的‘wright’传统),二是安装时会自动执行脚本(postinstall 里跑 sync-skills.mjs)。虽然不是高危,但安装后它会操控 Figma 和浏览器,建议留意。The static scan found two medium risks: the project runs a script during installation and can control a browser. Review the code before using it in production.

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

03 OCT 202603 OCT 2026

增长GROWTH

+52.2%+52.2%

964 → 1.5k stars · 48 个快照964 → 1.5k stars · 48 snapshots

状态STATUS

持续活跃Active

质量 A-Quality A-

近 7 天有 6 次提交,项目仍在活跃更新中。Free and open-source (MIT license)

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/awdr74100/figwright
原始数据哈希Raw data hash
87d284881bf53f3cce619f15b69b6d86
解析时间Parsed at
2026-11-19T23:56:18.256Z
最后一次验证Last verified
2026-11-19T22:14:42.458Z
增长测量时间Growth measured
2026-10-23T23:43:00.984Z
发现查询Discovery queries
focus:design:repo:figma-mcp, focus:motion:code:framer-motion
分类来源Category source
rules
焦点Focus
design · motion · web (12)
完整解析证据 JSONFull parse evidence JSON
{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude/"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 7,
      "ai-tools": 4,
      "dev-tools": 0,
      "indie-web": 1,
      "skill-agent": 9,
      "productivity": 0
    },
    "primary": "design",
    "secondary": "figma"
  },
  "localRuntime": null,
  "skillMdTotal": 4,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 13,
    "browser": 0,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "4 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 15 markdown files",
      "weight": 0.75
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "README ships an mcpServers config for this server",
      "weight": 0.7
    },
    {
      "signal": "MCP topic + README",
      "weight": 0.6
    },
    {
      "signal": ".mcp.json (configures servers it uses)",
      "weight": 0.3
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    ".claude/skills/figma-typings-audit/SKILL.md",
    ".claude/skills/mcp-sdk-audit/SKILL.md",
    "skills/figma-build/SKILL.md",
    "skills/figma-codegen/SKILL.md"
  ],
  "skillMdFetched": 4
}