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 Swair/prosophor --skill md2papergit clone --depth 1 https://github.com/Swair/prosophorWrote 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/swair/prosophor/md2paper)<a href="https://agentmods.dev/skills/swair/prosophor/md2paper"><img src="https://agentmods.dev/badge/skills/swair/prosophor/md2paper/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/swair/prosophor/md2paper"><img src="https://agentmods.dev/badge/skills/swair/prosophor/md2paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01862 |
| Opus 5 | $0.00022 | $0.00931 |
| Sonnet 5 | $0.00009 | $0.00372 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
md2paper 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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown to Academic Paper Converter
Convert Markdown files to properly formatted Word documents (and optionally PDF). Auto-detects language from filename (Chinese characters = CN format, otherwise EN/arXiv format).
When to Use
- User asks to convert
.mdfiles to.docx/ Word / paper / PDF format - User wants to generate academic papers, white papers, or theory documents from Markdown
- User references paper formatting standards (Chinese academic / arXiv style)
Prerequisites
pip install python-docx lxml docx2pdf
Usage
# Word only
python .claude/skills/md2paper/md2docx.py <input.md> <output.docx>
# Word + PDF
python .claude/skills/md2paper/md2docx.py <input.md> <output.docx> --pdf
arXiv Format Reference (learned from 2604.21804v1.pdf)
Title & Author Block
Phenomenological Detector Design and Optimization in Vertically-Integrated...
(centered, normal weight, ~14-16pt)
Wonyong Chung (name)
Princeton University (affiliation)
Jadwin Hall, Washington Road, ... (address)
[email protected] (email)
Qibin Liu (next author, same pattern)
SLAC National Accelerator Laboratory
...
Abstract Block
Abstract ("Abstract" title case, bold, standalone)
We present the first implementation... (flush-left, NO indent, single paragraph)
Body Text
1 Introduction (decimal section numbering)
High-energy physics (HEP) research... (first-line indent, justified)
2.1 Bilevel optimization... (hierarchical numbering)
Figure & Table Captions
Figure 1: Bilevel detector optimization... (full "Figure", bold colon separator, centered below)
Table 1: Optimization parameters... (full "Table", bold colon separator, centered above)
Format Specifications
Chinese Format (paperol_cn_v2.0)
What ships with it
4 files 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.
- 10d ago First seen · 182 lines · 0 tokens per session scan A b82b59deb25d
md2paper is a skill published in the GitHub repository Swair/prosophor (59 stars, last pushed 10d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,862 once invoked, about $0.0002 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
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
nano-pdf
Edits PDF files using natural-language instructions via the nano-pdf CLI. Supports modifying text, changing titles, fixing typos, and updating content on specific pages. Use when the user wants to edit a PDF, modify PDF content, update PDF text, fix a typo in a PDF, change a PDF title, or rewrite part of a PDF page.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.