菜单
Extract and validate URLs from text, presenting results in a clear format with brief descriptions and image previews.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Crawl and analyze a website's visual design system from a given URL, identifying design style, color system, typography, component styles, and UI patterns. Output a structured design specification document for UI generation. Suitable for competitive design analysis, UI restoration, design system reverse engineering, style migration, and similar scenarios.
Agent Skills standard reference guide. Covers SKILL.md specification format, progressive loading, skill discovery and activation, authoring best practices, quality evaluation, description optimization, and more.
Loop Engineering AI programming paradigm guide. Covers the core concepts of transitioning from single prompt calls to autonomous loop systems, key components, loop patterns, configuration examples, and anti-patterns.
A professional email writing assistant. Based on the user's email purpose and content points, writes clear, concise, and polite emails covering subject, body, and attachment notes, adapted to different audiences and scenarios.
A senior industry research consultant. Conducts in-depth analysis of specified industries, covering development history, industry trends, competitive landscape, and technological innovation, and outputs forward-looking, actionable recommendations.
A professional job description (JD) writing assistant. Based on job title and recruitment requirements, writes precise, professional, and compelling job descriptions covering three modules: job responsibilities, qualifications, and key skills.
| name | url-extractor |
| description | Extract and validate URLs from text, presenting results in a clear format with brief descriptions and image previews. |
Quickly extract all URLs from text, validate them, and present results in a structured format.
Use when users need to "extract links", "extract URLs", "find web addresses", or "extract links from text".
Quickly identify and extract all possible URLs from user-provided text:
https:// or http://)example.com/path)Validate extracted URLs:
web_fetch tool to access each URL and confirm accessibilityContent-Type: image/*), mark it as previewable❌ UnreachableOutput in a structured format:
## Extraction Results
N URLs extracted (M accessible, K unreachable)
| # | URL | Status | Title/Description |
|---|-----|--------|-------------------|
| 1 | https://example.com | ✅ | Example Domain |
| 2 | https://example.com/img.png | ✅ 🖼️ | Image Preview |
| 3 | https://broken.link | ❌ | Unreachable |
### Image Previews
[For image URLs, use the image tool to show previews]