设计资源DESIGN· INSPIRATION
xdx888999/xdx-lab-design-skill
给 AI 助手用的设计风格库,内含 50 种风格与 20 位大师方法,帮它按规范生成网页、PPT、海报。A design-style library for AI coding tools: 50 curated specs, 20 master methods, and 120+ style references turn a short prompt into a visual direction.
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
按宋代水墨等风格做网页海报
未指定风格时推荐两三个方向
吸取大师方法设计产品页面
把两种风格叠加成一套新规范
复制一份 DESIGN.md 到项目中使用
Pick one of 50 curated styles for your next layout.
Apply a master designer's method to a page or poster.
Combine a style with a designer method for mixed visual rules.
Get a custom design spec for styles outside the curated list.
Export PNGs using browser screenshots or Canvas when bitmap output is needed.
上手GET STARTED
git clone https://github.com/xdx888999/xdx-lab-design-style-skill.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 browserSKILL.md
- 如果需要位图交付,再用浏览器截图、Playwright、Canvas 或可用图像工具导出 PNG。
静态扫描命中一项中等风险:文档提到需要位图交付时可用浏览器截图、Playwright、Canvas 或图像工具导出 PNG,意味着技能可能让 AI 操作浏览器;但这只是可选用例,未发现强制执行的代码。仓库没有服务端代码,本地克隆后风险可控。The static scan flagged a medium item: the docs mention using browser screenshots, Playwright, Canvas, or image tools to export PNG for bitmap deliverables. That can be a normal image-export path, but browser control is worth reviewing before you run this in a sensitive environment.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+25.0%+25.0%
32 → 40 stars · 49 个快照32 → 40 stars · 49 snapshots
状态STATUS
长期未更新Not updated
质量 AQuality A
仓库把 50 种精选风格、20 位设计大师方法论和 120+ 风格知识库整理成 AI 可直接读取的规则文件,让设计风格统一且可复用。One repo includes 50 curated styles, 20 master designer methods, and a 120+ style knowledge base.
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …向所有智能体的设计风格 Skill,适用于 Codex / Claude Code / Cursor / v0 / Bolt / Lovabl…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 6,
"ai-tools": 1,
"dev-tools": 1,
"indie-web": 1,
"skill-agent": 1,
"productivity": 0
},
"primary": "design",
"secondary": "inspiration"
},
"localRuntime": "install: git-clone",
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 1,
"design": 10,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}