# PDF Explore

Read, extract, and cross-check content across scientific PDFs.

- Repository: https://github.com/Companion-Inc/feynman (10055 stars)
- Category: Data and ML
- License: MIT
- Last updated: 2026-10-31
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Companion-Inc/feynman --skill pdf-explore -g -a claude-code -y`
Codex: `npx skills add Companion-Inc/feynman --skill pdf-explore -g -a codex -y`
Cursor: `npx skills add Companion-Inc/feynman --skill pdf-explore -g -a cursor -y`
Gemini CLI: `npx skills add Companion-Inc/feynman --skill pdf-explore -g -a gemini-cli -y`

## Description

Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# PDF Explore

Use this skill when a PDF answer depends on more than one page or section.

Workflow:

1. Parse or inspect the full PDF enough to map title, abstract, methods, figures, tables, supplement references, and citations.
2. Extract the exact pages and regions that support the answer.
3. Keep table values, figure labels, accession IDs, and quoted snippets tied to page numbers.
4. Cross-check claims against methods, captions, supplement text, and cited papers when the conclusion depends on them.
5. Save extracted notes, annotations, and provenance as artifacts.

Do not answer from a single visible page when the question spans methods, figures, or supplements.