academic-pdf-to-gfm

academic-pdf-to-gfm is a skill for Claude Code from terrylica/cc-skills. It costs 35 tokens per session (7,224 once invoked), scanned A, original, MIT.

A workflow for converting academic PDF papers into GitHub-renderable Markdown with LaTeX equations, figures, and validated output. PDF is a fixed-layout document format, and GitHub-renderable Markdown is text that GitHub can display as a formatted page.

In plain words
What is it for?
Use it to turn research papers into readable GitHub documents, render and inspect pages, preserve mathematical notation, include figures, and check the resulting Markdown.
Why use it?
It handles pages with mixed text, tables, figures, and equations more carefully than applying one extraction method to the whole paper.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/terryli/eon/quantml/data/papers/a599/b338e44af70d8e9c87be3c5417bde7864b2c92074e1346703f3e2b641e3d.pdf.

Part of the doc-tools plugin — 13 skills shipped together , and of cc-skills

Good fit Use it to turn research papers into readable GitHub documents, render and inspect pages, preserve mathematical notation, include figures, and check the resulting Markdown.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add terrylica/cc-skills
Claude Code
/plugin install doc-tools

Made for: Claude Code.

Or install doc-tools, the plugin that ships this one along with the rest of its 13 skills.

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.

agentmods badge for academic-pdf-to-gfm

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/academic-pdf-to-gfm/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/academic-pdf-to-gfm)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/academic-pdf-to-gfm"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/academic-pdf-to-gfm/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.

agentmods 80×15 button for academic-pdf-to-gfm

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/academic-pdf-to-gfm"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/academic-pdf-to-gfm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,224 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.07224
Opus 5 $0.00017 $0.03612
Sonnet 5 $0.00007 $0.01445
Haiku 4.5 $0.00003 $0.00722

Measured 7d ago against content hash 04320d55ce38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

academic-pdf-to-gfm 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/validate-math.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/doc-tools/skills/academic-pdf-to-gfm/SKILL.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Academic PDF → GitHub GFM Conversion

A battle-tested workflow for converting academic/research PDF papers into GitHub-renderable GFM markdown with inline figures, mathematically correct LaTeX, and validated output.

Battle-tested on: López de Prado (2026) "How to Use the Sharpe Ratio" — 51 pages, 82 equations, 8 figures.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Quick Start — Per-Page Routing Workflow

Do NOT try to apply a single extraction method to the entire PDF. Modern academic papers mix text, tables, and figures; route each page individually.

Step 1: Render all pages at 300 DPI

# Generate PNG for every page at 300 DPI
uv run --python 3.14 --with pymupdf python3 << 'EOF'
import fitz, os
doc = fitz.open('paper.pdf')
os.makedirs("pages", exist_ok=True)
for i in range(len(doc)):
    pix = doc[i].get_pixmap(matrix=fitz.Matrix(300/72, 300/72), alpha=False)
    pix.save(f"pages/page{i:04d}.png")
    print(f"Page {i}: {pix.width}×{pix.height}")
EOF

Step 2: Detect page type for each page

# Locate the Unlimited-OCR script. If installed via marketplace, it will be in the cc-skills plugin directory.
# If running from the cc-skills repo directly:
S=${S:-~/eon/cc-skills/plugins/unlimited-ocr/scripts/unlimited_ocr.py}

# For each page, run Unlimited-OCR and inspect the <|det|> markers
for img in pages/page*.png; do
    echo "=== $(basename $img) ==="
    uv run --no-project $S parse --input "$img" --collapse-math-spacing --quiet 2>&1 | \
        grep "<|det|>" | cut -d'>' -f2 | cut -d' ' -f1 | sort | uniq -c
done

Step 3: Route each page

Based on the detected <|det|> markers:

Detected Route to Command
text only (no equation, image, chart) pymupdf4llm or pdftotext See Tool Comparison below
equation or table present Unlimited-OCR (with --table-format pipe) uv run --no-project $S parse --input page.png
image or chart present Segment + describe Use unlimited-ocr-segment-figure skill + vision model
Mixed (table + image) Unlimited-OCR for table + segment for images Split the output, route images separately

Read the full file on GitHub · 537 lines

Files

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.

Changes

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.

  1. 7d ago First seen · 537 lines · 35 tokens per session scan A 04320d55ce38

Subscribe to this mod's changes

academic-pdf-to-gfm is a skill published in the GitHub repository terrylica/cc-skills (73 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 7,224 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 2026-09-05.