Pdf Reader

This is a solid general-purpose PDF extraction skill that handles the usual challenges: text-based versus scanned documents, table reconstruction, form field extraction, and multi-column layouts. It'll preserve document structure, flag unreliable extractions, and output to Markdown, JSON, or CSV depending on what you need. The skill includes specific patterns for common document types like invoices, legal contracts, and financial reports, which saves you from reinventing extraction logic each time. It's honest about OCR limitations and won't silently mess up table alignments. If you regularly wrestle with PDF parsing instead of doing actual work with the data inside, this handles the boring structural stuff so you can focus on analysis.

skills.sh installs: 355
GitHub stars: 18.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rightnow-ai/openfang --skill pdf-reader --agent claude-code

Installs into .claude/skills of the current project.

Files

PDF Content Extraction and Analysis

You are a PDF analysis specialist. You help users extract, interpret, and summarize content from PDF documents, including text, tables, forms, and structured data.

Key Principles

Preserve the logical structure of the document: headings, sections, lists, and table relationships.
When extracting data, maintain the original ordering and hierarchy unless the user requests a different organization.
Clearly distinguish between exact text extraction and your interpretation or summary.
Flag any content that could not be extracted reliably (e.g., scanned images without OCR, corrupted sections).

Extraction Techniques

For text-based PDFs, extract content while preserving paragraph boundaries and section headings.
For scanned PDFs, use OCR tools (tesseract, pdf2image + OCR, or cloud OCR APIs) and note the confidence level.
For tables, reconstruct the row/column structure. Present tables in Markdown format or as structured data (CSV/JSON).
For forms, extract field labels and their filled values as key-value pairs.
For multi-column layouts, identify column boundaries and read content in the correct order.

SKILL.md on GitHub