What is literature-pdf-ocr-library?

A tool for building a traceable library of academic papers from legally accessible sources such as arXiv, a public repository for research papers. It downloads papers, extracts their text with OCR, and organizes metadata and Markdown files.

Use it to search for papers, download open-access PDFs, convert PDFs or page images into Markdown, and organize them into named research collections.

It creates a structured, AI-readable literature collection instead of leaving papers and references scattered or relying on unverifiable sources.

literature-pdf-ocr-library — Skill for Codex by LigphiDonk

Install

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.

Any agent

npx skills add LigphiDonk/Oh-my--paper --skill literature-pdf-ocr-library

Clone the repo

git clone --depth 1 https://github.com/LigphiDonk/Oh-my--paper

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library/github.svg)](https://agentmods.dev/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library)

Your own site

<a href="https://agentmods.dev/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/literature-pdf-ocr-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,069 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.01069
Opus 5	$0.00054	$0.00535
Sonnet 5	$0.00022	$0.00214
Haiku 4.5	$0.00011	$0.00107

Measured 12d ago against content hash d5eaf1792762, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

literature-pdf-ocr-library 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 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/build_library_index.py, scripts/ingest_literature_library.py, scripts/literature_lib.py, …), 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.

skills/literature-pdf-ocr-library/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Literature PDF OCR Library

Overview

Use this skill to build a real, traceable literature corpus instead of fabricating references or scraping arbitrary publisher pages. The default workflow is: narrow the topic, search official or stable APIs, download only legally accessible PDFs, run OCR or layout parsing, then emit a clean Markdown library with machine-readable metadata.

Canonical Directory Layout

In Oh My Paper projects, the corpus always lives under .pipeline/literature/<corpus-name>/.
In standalone projects, use research/literature/<corpus-name>/.
Never dump papers into the root or a flat directory without a corpus name.

.pipeline/
  literature/
    <corpus-name>/              ← one folder per topic/session, e.g. "humanoid-locomotion"
      search_results.json       ← raw search/ID-lookup results
      library_index.json        ← consolidated index for the whole corpus
      library_index.jsonl
      papers/
        <arxiv-id>-<title-slug>/   ← one folder per paper
          metadata.json
          paper.pdf
          ocr/                  ← OCR output lives here, next to the PDF
            paper/
              doc_0.md          ← main OCR markdown (PaddleOCR: multiple pages)
              manifest.json
            doc_0.md            ← pdfminer fallback: single flat file

Rules:

--out-dir always points to .pipeline/literature/<corpus-name>/ — never to .pipeline/literature/ directly.
OCR output lives inside the paper's own folder (papers/<slug>/ocr/), not in a top-level ocr/ directory.
After OCR, record each paper's ocr/ path in literature_bank.md so agents can read the actual content.

Commands

# Download by arXiv IDs (recommended when IDs are known from web search)
python .claude/skills/literature-pdf-ocr-library/scripts/search_and_download_papers.py \
  --arxiv-ids 2502.13817 2501.14459 \
  --out-dir .pipeline/literature/my-corpus \
  --download-pdfs

# Download by query
python .claude/skills/literature-pdf-ocr-library/scripts/search_and_download_papers.py \
  --query "humanoid locomotion reinforcement learning" \
  --out-dir .pipeline/literature/my-corpus \
  --limit 20 --sources arxiv semanticscholar openalex hf_daily \
  --download-pdfs

# OCR: PaddleOCR API (best quality)
export PADDLEOCR_TOKEN="<token>"  # ask user, never hardcode
python .claude/skills/literature-pdf-ocr-library/scripts/paddleocr_layout_to_markdown.py \
  .pipeline/literature/my-corpus/papers/*/paper.pdf \
  --output-dir .pipeline/literature/my-corpus/papers \
  --skip-existing

# OCR: pdfminer fallback (text-only, no layout — confirm with user first)
python .claude/skills/literature-pdf-ocr-library/scripts/paddleocr_layout_to_markdown.py \
  .pipeline/literature/my-corpus/papers/*/paper.pdf \
  --output-dir .pipeline/literature/my-corpus/papers \
  --fallback-pdfminer

# Build index
python .claude/skills/literature-pdf-ocr-library/scripts/build_library_index.py \
  --library-root .pipeline/literature/my-corpus

Read the full file on GitHub · 97 lines

Files

What ships with it

8 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.

12d ago First seen · 97 lines · 108 tokens per session scan A d5eaf1792762

Subscribe to this mod's changes

literature-pdf-ocr-library is a skill published in the GitHub repository LigphiDonk/Oh-my--paper (724 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 1,069 once invoked, about $0.0005 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.

Documents PDF Research

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.

K-Dense-AI/scientific-agent-skills · 56 tokens

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.

microsoft/agent-framework · 82 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

pdf-extract-create-workflow

Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.

HKUDS/OpenSpace · 22 tokens

document-direct-python

Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.

HKUDS/OpenSpace · 20 tokens

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.

superlinked/sie · 64 tokens