Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/aduermael/herm/beautiful-pdfs)<a href="https://agentmods.dev/skills/aduermael/herm/beautiful-pdfs"><img src="https://agentmods.dev/badge/skills/aduermael/herm/beautiful-pdfs/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/aduermael/herm/beautiful-pdfs"><img src="https://agentmods.dev/badge/skills/aduermael/herm/beautiful-pdfs.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 | $0.00020 | $0.00994 |
| Opus 5 | $0.00010 | $0.00497 |
| Sonnet 5 | $0.00004 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
beautiful-pdfs scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beautiful PDFs
Use this skill when the user asks for a PDF, printable report, invoice, brief, handout, form, one-pager, or visual document.
Workflow
- Use the available Luau globals directly. Do not call
require; usefs.read,fs.write, anddoc.renderFile. - Confirm HTML-to-PDF rendering is available before investing in a long document. If unsure, create a tiny HTML file in
/tmpand run:fs.write("/tmp/pdf-smoke.html", "<!doctype html><meta charset=\"utf-8\"><h1>PDF smoke test</h1>") doc.renderFile({source="/tmp/pdf-smoke.html", target="/tmp/pdf-smoke.pdf"}) print(fs.exists("/tmp/pdf-smoke.pdf")) - If rendering reports
platform not supported, policy denial, or another capability error, stop PDF-generation work. Tell the user that PDF creation is unavailable in this session; do not try image-based PDF, font fetching, network downloads, package installs, browser printing, external renderers, or OS tools. - Create semantic HTML. Use real document structure: headings, sections, tables, figures, captions, footers, and page-break rules.
- Put presentation in CSS. Prefer restrained typography, clear spacing, durable contrast, and print-safe colors. Avoid huge hero layouts unless the user explicitly asks for a cover page.
- Write source HTML to a temporary or hidden build path unless the user explicitly asks for editable source files.
- Render HTML to PDF with the available document module. Start by checking
help()anddoc.help()if the exact API is not already visible in context. - Prefer
doc.renderFile({source="/tmp/report.html", target="/home/herm/report.pdf"})for saved HTML-to-PDF output. It detectshtml -> pdffrom the file extensions. - Inspect the resulting PDF metadata or page count when practical before telling the user it is ready.
Luau Snippets
Read and adapt the bundled print baseline when useful:
local css = fs.read("/skills/beautiful-pdfs/print.css")
Build source HTML in /tmp so the user only sees the PDF unless they ask for source files:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 83 lines · 20 tokens per session scan A f1d528fe4f1c
beautiful-pdfs is a skill published in the GitHub repository aduermael/herm (232 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 994 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Read, extract, split, merge, rotate, watermark, fill, OCR, or create PDF files with verification of page counts and text extraction.
ocr-and-documents
Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
Read, create, inspect, render, and verify PDF files where visual layout matters, including fillable AcroForms. Use Poppler rendering plus Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.
pdf-official
Use this skill to read, compose, transform, or fill a PDF: extracting text, tables, metadata, or images; merging, splitting, rotating, cropping, watermarking, or compressing pages; building a report, invoice, or certificate; filling form fields or overlaying values on a scan; running optical character recognition…