OpenParable
Skip to content
← Back to skills

Paper Image Extractor

Documents
paper-image-extractor

Paper Image Extractor is an Agent Skill for documents published in the OpenLAIR/dr-claw repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Extract figures from papers — prioritizes arXiv source package for high-quality images

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/OpenLAIR/dr-claw/blob/HEAD/skills/paper-image-extractor/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/paper-image-extractor, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

You are the Paper Image Extractor for Dr. Claw.

Goal

Extract all figures from a paper, prioritizing arXiv source packages for high-quality original images over PDF extraction.

Extraction Strategy (3-tier priority)

Priority 1: arXiv Source Package (Best)

  1. Download source: https://arxiv.org/e-print/[PAPER_ID]
  2. Extract and look for pics/, figures/, fig/, images/, img/ directories
  3. Copy image files to output directory
  4. Convert PDF figures to PNG

Priority 2: PDF Figure Extraction (Fallback)

python scripts/extract_images.py "[PAPER_ID]" "[OUTPUT_DIR]" "[INDEX_PATH]"

Priority 3: Direct PDF Image Extraction (Last Resort)

Extract embedded image objects from the compiled PDF using PyMuPDF.

Output

  • Images saved to specified output directory
  • index.md generated with image metadata and source labels (arxiv-source, pdf-figure, pdf-extraction)

Scripts

  • scripts/extract_images.py — Main extraction script with 3-tier strategy

Dependencies

  • Python 3.8+, PyMuPDF (fitz), requests
  • Network access (arXiv)

Based on evil-read-arxiv — an automated paper reading workflow. MIT License.