Borrowing it
Nothing to install: this file belongs to ChinaCarlos/figma-agent-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChinaCarlos/figma-agent-kit/main/.cursor/skills/figma-ui-restore/SKILL.mdgit clone --depth 1 https://github.com/ChinaCarlos/figma-agent-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chinacarlos/figma-agent-kit/figma-ui-restore)<a href="https://agentmods.dev/skills/chinacarlos/figma-agent-kit/figma-ui-restore"><img src="https://agentmods.dev/badge/skills/chinacarlos/figma-agent-kit/figma-ui-restore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chinacarlos/figma-agent-kit/figma-ui-restore"><img src="https://agentmods.dev/badge/skills/chinacarlos/figma-agent-kit/figma-ui-restore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00135 | $0.04305 |
| Opus 5.5 | $0.00054 | $0.01722 |
| Sonnet 5.5 | $0.00027 | $0.00861 |
| Haiku 4.5 | $0.00014 | $0.00430 |
Grade A, and why
figma-ui-restore scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma UI 1:1 还原(Figma Agent Kit)
沟通:简体中文。
定位
本 Skill 指导 Agent 用 本仓库配套工具链完成通用 UI 稿还原:
| 组件 | 用途 |
|---|---|
| Figma Agent Kit 插件 | Figma Desktop 中运行;桥客户端、可选切图 UI |
figma-agent-mcp |
stdio MCP:读节点 / 截图 / save_screenshots 等 |
不是:某一活动仓专用流水线;不绑定 partyActivity / hh-active / fe-prd-plan。
是:任意前端项目里「对着 Figma scope 做结构还原 + 切图 + 验收」的通用流程。
前置文档(需要时 Read):
- 上手 / 工具表:仓库
docs/zh/getting-started.md、docs/zh/tools.md或文档站 - 桥协议:
docs/zh/bridge-protocol.md
一句话总览
锁 scope →(确认门)→ list_files → get_node 读结构 → TEXT 全量归类
→ 切图打标 → get_screenshot 基准图 → save_screenshots×3 落盘
→ bounds 落码 → 分块对照 → 验收清单勾完才能说「1:1」
默认 figmaMode: strict。仅用户明文「快速 / fast」时可压缩步骤 3 的冗长层级表、可省略步骤 5 落盘基准图;不得跳过 3b TEXT 清单与步骤 4 切图粒度,不得整页一图兜底。
流程总图
flowchart TD
A[用户给 Figma URL] --> B[解析 scopeNodeId]
B --> C{实现向确认门?}
C -->|未确认| D[禁止 get_node / 切图 / 落码<br/>仅 list_files + 定输出目录]
C -->|已确认| E[list_files → connected fileKey]
E --> F[get_node 读子树结构 + bounds]
F --> G[步骤 3b TEXT 全量清单归类]
G --> H[步骤 4 非 TEXT 打标 skin/whole-btn/panel-bg]
H --> I[get_screenshot 基准图]
I --> J[save_screenshots scale3 落 images]
J --> K[步骤 7 bounds→样式单位落码]
K --> L[步骤 7b 分块对照基准图]
L --> M{块通过?}
M -->|否| K
M -->|是| N[对照验收清单]
N --> O{全通过?}
O -->|否| K
O -->|是| P[可写「已按 scope 1:1 对照验收」]
0. 前置检查(工具链)
- [ ] Figma Desktop 已打开目标文件(设计模式;勿依赖易休眠的浏览器标签)
- [ ] 已 Import 并运行 Plugins → Development → Figma Agent Kit
- [ ] 插件显示 MCP Bridge 已连接(绿色)
- [ ] Cursor(或其它宿主)已配置 figma-agent-mcp:npx -y figma-agent-mcp
- [ ] MCP 面板可见工具(约 37 tools)
- [ ] node-id:URL 中 1-234 → MCP 用 1:234
MCP 调用约定
- 优先使用已连接的 figma-agent-mcp(宿主里名称可能是
figma-agent-mcp/user-figma-agent-mcp等)。 - 先
list_files,用返回的 connectedfileKey;勿只用 URL 里的 fileKey(易出现 No plugin connected)。 - 默认端口 1998(与
bridge.config.json/ 插件构建一致);自定义端口须 MCP 与插件同改。 - 调用前用
GetMcpTools(若环境要求)确认参数 schema。
常用工具:
| 用途 | 工具 |
|---|---|
| 探活 / 取 fileKey | list_files |
| 读选区 | get_selection |
| 读节点树 | get_node(nodeIds,可选 depth) |
| 选中 / 聚焦 | set_selection、scroll_and_zoom_into_view |
| 视觉基准(Agent 侧预览) | get_screenshot(默认 PNG,scale 默认 2;基准建议 scale 1~2) |
| 切图落盘 | save_screenshots(scale: 3,PNG compress: true) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 304 lines · 135 tokens per session scan A fcc6f9f2bd86
figma-ui-restore is a skill published in the GitHub repository ChinaCarlos/figma-agent-kit (6 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 4,305 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
figma-ui-restore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| figma-ui-restoreChinaCarlos/figma-agent-kit | Skill | 6 | 2mo ago | MIT | A | 135 | Cursor |
| refero-designreferodesign/refero_skill | Skill | 336 | 22d ago | MIT | A | 191 | Claude Code, Codex |
| tailwind-design-systemcalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 42 | Claude Code, Codex |
| motion-graphicscalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 187 | Claude Code, Codex |
| visual-stylecalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 136 | Claude Code, Codex |
| vercel-composition-patternscalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 58 | Claude Code, Codex |
| web-design-guidelinescalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 44 | Claude Code, Codex |