Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KaimingWan/oh-my-kiro --skill omk-pdf-gengit clone --depth 1 https://github.com/KaimingWan/oh-my-kiroWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kaimingwan/oh-my-kiro/omk-pdf-gen)<a href="https://agentmods.dev/skills/kaimingwan/oh-my-kiro/omk-pdf-gen"><img src="https://agentmods.dev/badge/skills/kaimingwan/oh-my-kiro/omk-pdf-gen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kaimingwan/oh-my-kiro/omk-pdf-gen"><img src="https://agentmods.dev/badge/skills/kaimingwan/oh-my-kiro/omk-pdf-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.01270 |
| Opus 5 | $0.00043 | $0.00635 |
| Sonnet 5 | $0.00017 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
omk-pdf-gen scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['weasyprint', html_tmp, output_path], check=True) How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Generation Skill
Trigger Examples
- "帮我生成一个报价 PDF"
- "把这个内容导出成 PDF"
- "PDF 中文乱码怎么办"
- "generate a comparison PDF for this customer"
- "create a budget proposal PDF"
Approach: HTML + weasyprint
Use HTML + CSS → weasyprint pipeline. Do NOT use reportlab for documents containing CJK text.
Why:
- reportlab CID fonts (STSong-Light) have incomplete glyph coverage — symbols like
•render as garbage (e.g. "煉") - reportlab cannot read macOS SIP-protected TTC fonts (PingFang etc.)
- reportlab
canvasAPI requires manual coordinate positioning — fragile and ugly - weasyprint uses system fontconfig — correct font resolution out of the box
Workflow
Step 1: Write HTML string in Python
HTML = """\
<!DOCTYPE html>
<html lang="zh">
<head><meta charset="utf-8">
<style>
@page { size: A4; margin: 2cm 2.2cm; }
body { font-family: "Hiragino Sans GB", "Heiti SC", "Noto Sans CJK SC", sans-serif; ... }
</style></head>
<body>...</body></html>
"""
Step 2: Write to temp HTML, convert, clean up
import subprocess, os
html_tmp = output_path.replace('.pdf', '.html')
with open(html_tmp, 'w', encoding='utf-8') as f:
f.write(HTML)
subprocess.run(['weasyprint', html_tmp, output_path], check=True)
os.remove(html_tmp)
Font Rules (Critical)
| Platform | CSS font-family | Notes |
|---|---|---|
| macOS | "Hiragino Sans GB", "Heiti SC" |
Verified via fc-list :lang=zh |
| Linux | "Noto Sans CJK SC", "WenQuanYi Micro Hei" |
Install fonts-noto-cjk if missing |
| Fallback | sans-serif |
Always include as last resort |
Never use these in weasyprint CSS:
-apple-system— weasyprint doesn't understand Apple system font aliases"PingFang SC"— fontconfig often can't resolve it even though macOS has it"STSong-Light"— CID font name, not a real font family for CSS
Before generating, verify CJK fonts are available:
fc-list :lang=zh family | head -10
Styling Best Practices
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 122 lines · 85 tokens per session scan A 5f60d96e7e11
omk-pdf-gen is a skill published in the GitHub repository KaimingWan/oh-my-kiro (103 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 1,270 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.