dannote/figma-use

• highreadme#1

  Reposition the README's opening to clearly state the core function for AI agents

  原因：

  当前

  # figma-use
  
  > **⚠️ Figma 126+ blocks remote debugging.** figma-use still works via `figma-use daemon start --pipe`. Or skip Figma entirely with **OpenPencil** — an open-source design editor that reads and writes .fig files, with built-in AI and P2P collaboration.
  
  CLI for Figma. Control it from the terminal — with commands or JSX.

  复制粘贴的修复

  复制

  # figma-use
  
  Control Figma from the command line. Full read/write access for AI agents — create shapes, text, components, set styles, export images. 100+ commands.
  
  > **⚠️ Figma 126+ blocks remote debugging.** figma-use still works via `figma-use daemon start --pipe`. Or skip Figma entirely with **OpenPencil** — an open-source design editor that reads and writes .fig files, with built-in AI and P2P collaboration.
  
  CLI for Figma. Control it from the terminal — with commands or JSX.

  待办完成忽略
• hightopics#2

  Add more specific topics to improve categorization

  原因：

  当前

  ai-agents, automation, cli, design, figma

  复制粘贴的修复

  复制

  ai-agents, automation, cli, design, figma, programmatic-design, design-automation, ai-design-tools, figma-cli

  待办完成忽略
• mediumreadme#3

  Refine the 'Why' section to emphasize unique read/write capabilities for AI agents

  原因：

  当前

  Figma's official MCP plugin can read files but can't modify them. This one can.
  
  LLMs know CLI. LLMs know React. This combines both.

  复制粘贴的修复

  复制

  ## Why
  
  **Full read/write access for AI agents:** Figma's official MCP plugin can read files but can't modify them. This one can, enabling AI agents to create shapes, text, components, set styles, and export images directly.
  
  **Optimized for LLMs:** LLMs know CLI and React. This combines both, offering compact commands and natural JSX descriptions for efficient generation and chaining of design tasks.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  I need to automate Figma design tasks using a command line interface programmatically.

  你：未被推荐
  AI 推荐顺序：

  1. Figma API
  2. requests (psf/requests)
  3. node-fetch (node-fetch/node-fetch)
  4. axios (axios/axios)
  5. create-figma-plugin (yuanqing/create-figma-plugin)
  6. Puppeteer (puppeteer/puppeteer)
  7. Playwright (microsoft/playwright)
  8. AppleScript
  9. AutoHotkey

  AI 推荐了 9 个替代方案，却始终没点名 dannote/figma-use。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  Seeking a tool for AI agents to generate and modify Figma designs with code.

  你：未被推荐
  AI 推荐顺序：

  1. Figma API
  2. OpenAI GPT-4
  3. Locofy.ai
  4. Anima App
  5. Builder.io
  6. Relume AI
  7. Supernova

  AI 推荐了 7 个替代方案，却始终没点名 dannote/figma-use。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of dannote/figma-use?

  pass
  ✓AI 明确点名了 dannote/figma-use

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts dannote/figma-use in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 dannote/figma-use

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo dannote/figma-use solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 dannote/figma-use

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？