# PDF Reader

> Use when the task requires reading, extracting, or grounding against local PDF files, including paper figures, legends, methods, and page-level evidence.

- Skill: `simplified-reasoning/pdf-reader` (Agent Skill)
- Install (CLI): `npx skillmds@latest add simplified-reasoning/pdf-reader`
- Raw SKILL.md: https://api.skillmd.com/api/skills/simplified-reasoning/pdf-reader/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: simplified-reasoning (https://skillmd.com/u/simplified-reasoning)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/simplified-reasoning/pdf-reader

---


# PDF Reader

Use this skill whenever the key material is a local PDF.

## When to use

- The task refers to a paper PDF, figure PDF, or scanned study material.
- The answer must rely on figure panels, legends, or methods beyond an abstract.
- The user asks what a figure or paper section is trying to show.

## Workflow

1. Read the PDF before answering from memory.
2. Extract only the pages or sections needed for the current question.
3. Tie claims back to page-level or section-level evidence when possible.
4. Distinguish direct PDF evidence from interpretation.
5. If the PDF is insufficient, ask for the highest-value missing material rather than generic follow-up.