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 fmschulz/omics-skills --skill pdf-to-mdgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote 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/fmschulz/omics-skills/pdf-to-md)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/pdf-to-md"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/pdf-to-md/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/fmschulz/omics-skills/pdf-to-md"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/pdf-to-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 80 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.03219 |
| Opus 5.5 | $0.00015 | $0.01288 |
| Sonnet 5.5 | $0.00008 | $0.00644 |
| Haiku 4.5 | $0.00004 | $0.00322 |
Grade A, and why
pdf-to-md 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- For the OCR API engine: `OCR_API_KEY` or `NELLI_API_KEY`, plus `curl`. How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pdf-to-md
Turn a PDF into Markdown. The right path depends on the document type and whether external document submission has been approved:
- Scientific paper → produce the canonical
paper-to-mdbundle (Markdown +section_audit.json+article.json) so it can feedcsag-extraction. Use LiteParse v2 locally unless the user explicitly approves the remote OCR API. - Any other PDF (reports, slides, letters, forms) → just convert to Markdown with LiteParse v2 for a fast, local, no-key result. Stop there.
LiteParse must be v2 (run-llama/liteparse,
the Rust rewrite with the LiteParse Python API and lit CLI). LiteParse v1 is a
different, unsupported API. liteparse_to_md.py pins liteparse>=2,<3 and refuses
to run on anything else, so uv run always provisions the right per-platform v2
binary inside the wheel — nothing to vendor or compile, and no API key. OCR is on by
default (bundled Tesseract).
LiteParse output is a draft, not the deliverable. LiteParse is a mechanical parser: it has no native Markdown, infers headings from font size/weight, and introduces artifacts (split words, broken hyphenation, dropped author blocks, merged columns). Whenever LiteParse is the engine, the LLM running this skill is responsible for shaping that draft into the right form — see "Shape the LiteParse output" below. The OCR API engine needs far less shaping.
Instructions
Step 0 — Classify the document and pick a path
| Document | Remote upload approved? | Path |
|---|---|---|
| Scientific paper / manuscript | yes, and an OCR key is configured | Mode A, OCR API with --allow-remote |
| Scientific paper / manuscript | no | Mode A, LiteParse v2 locally |
| Anything else | no remote upload needed | Mode B, LiteParse v2 locally |
Check for a key without printing it:
if [ -n "${OCR_API_KEY:-}${NELLI_API_KEY:-}" ]; then
echo "OCR key configured"
else
echo "No OCR key configured"
fi
What ships with it
11 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.
- fixtures/paper-missing-authors.md 317 B
- fixtures/paper.md 574 B
- references/article_schema.md 2.0 KB
- references/article.yaml 1.3 KB
- scripts/article_extraction.py 26 KB runs code
- scripts/build_section_audit.py 980 B runs code
- scripts/liteparse_to_md.py 13 KB runs code
- scripts/ocr_api_job.py 7.3 KB runs code
- scripts/populate_article_json.py 1.5 KB runs code
- scripts/render_pdf_pages_to_png.py 3.5 KB runs code
- scripts/validate_article_json.py 4.1 KB runs code
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.
- 1mo ago First seen · 268 lines · 38 tokens per session scan A 8abddc830f81
pdf-to-md is a skill published in the GitHub repository fmschulz/omics-skills (11 stars, last pushed 23d ago), licensed MIT. It adds 38 tokens to every session and 3,219 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
liteparse
Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
open-notebook
Organizes research with the self-hosted Open Notebook alternative to NotebookLM. Supports source ingestion (PDFs, web pages, audio, video, and Office documents), cited document chat, text and vector search, notes, custom transformations, and multi-speaker podcasts. Use when automating Open Notebook through its REST…
download-fulltext-pdf
A skill for downloading a research paper's complete PDF using an identifier such as a DOI, title, or BibTeX entry.