设计资源DESIGN· UI-KIT
Adityaraj0421/naksha-studio
在命令行里召唤30个设计角色，用命令生成UI、品牌和邮件模板。A virtual design team for AI coding tools, offering 30 roles and 70 commands for UI, UX, social, email, and data design.
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.
能力CAPABILITIES
生成网页或组件设计
将Figma设计转为代码
制作HTML邮件模板
创建社交媒体视觉
检查设计文件质量
Generate UI pages, dashboards, and landing pages from plain descriptions
Sync design tokens between Figma and your codebase
Create brand kits, color palettes, and design tokens
Produce social media visuals and email templates
Run design audits and generate developer handoff documents
上手GET STARTED
/plugin marketplace add https://github.com/Adityaraj0421/naksha-studio.git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.
使用限制LIMITATIONS
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
静态扫描STATIC SCAN
01控制浏览器Controls a browserreadme
| `/naksha-doctor [--fix]` | Plugin health check — validates command count, references, version consistency, allowed-tools; probes Playwrigh
02控制浏览器Controls a browserskills/design/SKILL.md
| `/design-compare <url1> <url2>` | Capture two live sites via Playwright, side-by-side design analysis: layout, type, color, UX patterns |
静态扫描发现两处中风险：`/naksha-doctor` 和 `/design-compare` 命令会通过 Playwright 控制浏览器，可能访问外部 URL，存在权限滥用和隐私泄露的可能。仅核验官方页面，未审计服务端代码；数据处理和费用以官网为准。The scan found it can control a browser via Playwright for health checks and design comparisons. This is a medium risk, so review the code before running it.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
04 NOV 202604 NOV 2026
增长GROWTH
+0.0%+0.0%
353 → 353 stars · 4 个快照353 → 353 stars · 4 snapshots
状态STATUS
持续活跃Active
安装后可在 Claude Code 等终端里直接调用 70 条设计命令，从生成立即页到 Figma 同步覆盖多种设计场景。30 roles and 70 commands cover UI, UX, social, email, and data design
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "cursor",
"evidence": "tree: .cursor/"
},
{
"agent": "claude-ai",
"evidence": "readme: …e-Plugin-blueviolet)](https://claude.ai/claude-code) [![Cursor](https…"
},
{
"agent": "windsurf",
"evidence": "readme: …dge/Cursor-Rules-black)]() [![Windsurf](https://img.shields.io/badge…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …/Windsurf-Rules-0099ff)]() [![Gemini CLI](https://img.shields.io/badge…"
},
{
"agent": "vscode",
"evidence": "readme: …ads it at session start. ### VS Code Copilot Copy `.github/copilo…"
},
{
"agent": "copilot",
"evidence": "readme: …oject's `.github/` directory. Copilot Chat and inline completions will a…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 16,
"ai-tools": 3,
"dev-tools": 4,
"indie-web": 1,
"skill-agent": 3,
"productivity": 0
},
"primary": "design",
"secondary": "ui-kit"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 1,
"design": 19,
"browser": 0,
"devtool": 7,
"security": 0,
"marketing": 3,
"productivity": 3
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 34 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/design/SKILL.md"
],
"skillMdFetched": 1
}