Skills
.Work. You
Rest

pdf-text-extraction-fallback

Community

Fallback PDF text extraction on restricted systems.

Data & Analytics#pdf#fallback#pymupdf#hpc#text-extraction#read-tool
AuthorKangOxford
Version1.0.0
Installs0

System Documentation

What problem does it solve?

On restricted systems where Claude Code's Read tool cannot render PDFs due to missing pdftoppm/poppler-utils, this Skill provides a Python-based fallback that converts PDFs to text via pymupdf and then feeds the resulting .txt to Read. It enables seamless content access in environments like locked-down HPCs or ARM machines without sudo privileges.

Core Features & Use Cases

  • Fallback text extraction using pymupdf to produce a sibling .txt file next to the original PDF.
  • Read the generated .txt with Read to access PDF content without system-level dependencies.
  • Triggers on errors mentioning pdftoppm, poppler-utils, or PDF rendering, or when a user asks to read a PDF on a machine without sudo privileges.

Quick Start

Trigger the fallback by converting the PDF to a sibling .txt with pymupdf and then read the resulting text with the Read tool.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: pdf-text-extraction-fallback
Download link: https://github.com/KangOxford/auto-quant-research/archive/main.zip#pdf-text-extraction-fallback

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.