项目创建于2026年4月，最近一次提交在2026年9月，持续迭代中。
12 built-in modes cover common design deliverables
独立开发者
Designers who want fast prototypes
目标用户 · 非用户评价Target user · not a testimonial
DESIGN/设计资源·MOTION
peixl/ifq-design-skills
12 种模式，零依赖——这个设计 skill 凭什么？12 modes, zero dependencies — what makes this design skill tick?
让AI agent根据普通提示生成HTML原型、幻灯片、仪表盘等设计产物。Turn plain prompts into HTML-first prototypes, slide decks, dashboards, and motion demos — zero-install for the core, export when you need.
怎么装：Install: npx skills add peixl/ifq-design-skills
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
历史不足Not enough history
只有 1 个快照，还不足以计算增长Only 1 snapshots so far — not enough to compute growth
讨论DISCUSSION
暂无None
还没有采集到外部讨论No external discussion collected yet
状态STATUS
持续活跃Active
质量 AQuality A
项目创建于2026年4月，最近一次提交在2026年9月，持续迭代中。12 built-in modes cover common design deliverables
03 / 它能帮你做什么03 / What it helps you do
把普通描述变成可交互的网页原型
生成幻灯片、仪表盘和动效演示
预览设计稿并检查占位符
导出PDF、PPTX或视频文件
产出可直接交付的视觉成品
Generate interactive prototypes from plain descriptions.
Build slide decks with ambient brand styling.
Create dashboards with live data placeholders.
Export designs to PDF, PPTX, or MP4 (opt-in).
Verify designs for placeholder and consistency issues.
04 / 谁在用04 / WHO IT’S FOR
项目创建于2026年4月，最近一次提交在2026年9月，持续迭代中。
12 built-in modes cover common design deliverables
独立开发者
Designers who want fast prototypes
目标用户 · 非用户评价Target user · not a testimonial
核心链路零依赖，无需安装Playwright等即可预览和验证HTML设计。
Core workflow needs zero dependencies — no Playwright or Python required
前端开发者
Product managers creating slide decks
目标用户 · 非用户评价Target user · not a testimonial
提供12种设计模式，覆盖原型、幻灯片、仪表盘、动效等，适合快速交付。
Includes automated validation and regression tests for consistent quality
设计师
Developers building dashboards
目标用户 · 非用户评价Target user · not a testimonial
项目创建于2026年4月，最近一次提交在2026年9月，持续迭代中。
12 built-in modes cover common design deliverables
内容创作者
Content makers needing motion demos
目标用户 · 非用户评价Target user · not a testimonial
不适合谁Not for同样来自文档，不是我们的判断Also from the docs, not our judgement
05 / 安装05 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
运行 `npx skills add peixl/ifq-design-skills` 即可安装。Install with one command: npx skills add peixl/ifq-design-skills, or clone the repository for your AI assistant.
06 / 限制与风险06 / Limits and risk
风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。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执行 Shell 命令Runs shell commandsreadme
- **Node/Python 脚本零 `child_process`、零 `eval`、零对外网络请求**；少数 shell 导出助手只在用户明确要 MP4/GIF/音频时调用 `ffmpeg` / `ffprobe`。内置模板默认不加载远程 CSS/JS——静态安全扫描（Cl
02控制浏览器Controls a browserreadme
**核心链路零依赖**：写 HTML → `npm run preview -- <file>` 打印 `file://` 预览 URL → `npm run verify:lite -- <file>` 扫占位符。**不需要装 Playwright、Chromium、Pytho
03控制浏览器Controls a browserSKILL.md
| Tier 1 | opt-in | Python + Playwright + Chromium | headless screenshots, console capture, multi-viewport checks |
扫描发现两处中等风险：skill 可以执行 Shell 命令（只在用户要求导出 MP4/GIF/音频时才调用 ffmpeg/ffprobe），也可以控制浏览器（只有用户主动启用 Tier 1 模式时才装 Playwright+Chromium 做截图检查）。这两个功能默认都是关闭的，文档也写了核心链路不需要那些工具。Static scan found medium risks: shell commands run only when you explicitly request MP4/GIF exports, and browser control requires opt-in Playwright installation. No remote CSS or JavaScript is loaded by default.
这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
依赖：Dependencies:ffmpeg-system
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …ll peixl/ifq-design-skills # Claude Code（personal） git clone https://g…"
},
{
"agent": "codex",
"evidence": "readme: …e/skills/ifq-design-skills # Codex CLI / OpenCode / 任何读取 AGENTS.md 的…"
},
{
"agent": "opencode",
"evidence": "readme: …-design-skills # Codex CLI / OpenCode / 任何读取 AGENTS.md 的 agent # 本仓…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 7,
"ai-tools": 0,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 10,
"productivity": 0
},
"primary": "design",
"secondary": "motion"
},
"localRuntime": null,
"skillMdTotal": 3,
"skillMdErrors": [
{
"path": ".well-known/agent-skills/ifq-design-skills/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": ".well-known/skills/ifq-design-skills/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 1,
"design": 11,
"browser": 1,
"devtool": 2,
"security": 1,
"marketing": 0,
"productivity": 2
},
"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",
".well-known/agent-skills/ifq-design-skills/SKILL.md",
".well-known/skills/ifq-design-skills/SKILL.md",
"SKILL.md"
],
"skillMdFetched": 3
}