菜单
Generate professional PDFs from Markdown, HTML, data, or code. Reports, invoices, contracts, and documents with best practices.
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。
Drive a headed Chromium via the agent-browser CLI — open/click/type/hover/scroll/screenshot/snapshot/eval/pdf/network-route. Use this for any web interaction; no native browser tool is exposed.
Search, install, and verify Debian or Ubuntu packages with apt-get in the container.
Search the web using DuckDuckGo. No API key required. Supports instant answers and HTML scraping modes. Privacy-focused search alternative.
Control the Linux desktop GUI using xdotool, wmctrl, dogtail, and scrot. Provides a window list, an accessibility-tree viewer (with coordinates) for finding buttons and text fields, a thin xdotool wrapper for actuating them, and a launcher helper that enables accessibility for Electron/Chromium apps.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Placeholder task skill.
基于 SOC 职业分类
| name | PDF Generator |
| slug | pdf-generator |
| version | 1.0.1 |
| homepage | https://clawic.com/skills/pdf-generator |
| description | Generate professional PDFs from Markdown, HTML, data, or code. Reports, invoices, contracts, and documents with best practices. |
| metadata | {"clawdbot":{"emoji":"📄","requires":{"bins":[]},"os":["linux","darwin","win32"]}} |
User needs to create, generate, or export PDF documents. Agent handles document generation from multiple sources (Markdown, HTML, JSON, templates), formatting, styling, and batch processing.
This skill ONLY:
This skill NEVER:
All code examples are reference patterns for the user to implement.
| Topic | File |
|---|---|
| Tool selection | tools.md |
| Document types | templates.md |
| Advanced operations | advanced.md |
| Source | Best Tool | Why |
|---|---|---|
| Markdown | pandoc | Native support, TOC, templates |
| HTML/CSS | weasyprint | Best CSS support, no LaTeX |
| Data/JSON | reportlab | Programmatic, precise control |
| Simple text | fpdf2 | Lightweight, fast |
Default recommendation: weasyprint for most HTML-based documents.
# CORRECT: semantic structure
html = """
<article>
<header><h1>Report Title</h1></header>
<section>
<h2>Summary</h2>
<p>Content...</p>
</section>
</article>
"""
# WRONG: style-first approach
html = "<div style='font-size:24px'>Report Title</div>"
/* Force page break before */
.new-page { page-break-before: always; }
/* Keep together */
.keep-together { page-break-inside: avoid; }
/* Headers never orphaned */
h2, h3 { page-break-after: avoid; }
# Example pattern for weasyprint
html = """
<html>
<head>
<title>Document Title</title>
<meta name="author" content="Author Name">
</head>
...
"""
@media print {
body {
font-family: 'Georgia', serif;
font-size: 11pt;
line-height: 1.5;
}
@page {
size: A4;
margin: 2cm;
}
.no-print { display: none; }
}
After generating any PDF:
| Trap | Consequence | Fix |
|---|---|---|
| Missing fonts | Fallback to defaults | Use web-safe fonts |
| Absolute image paths | Images missing | Use relative paths |
| No page size | Unpredictable layout | Set @page { size: A4; } |
| Large images | Huge files | Compress before use |
This is a reference skill. It provides patterns and guidance only.
Data that stays local:
This skill does NOT:
clawhub star pdf-generatorclawhub sync