skills.rest
JansenAnalytics
JansenAnalyticsCOMMUNITY
Explore all skills by this author →
GitHub

doc-reader

Extract and analyze text, tables, and metadata from PDF, DOCX, XLSX, images, and HTML documents.

5|Updated Apr 8, 2026
Search Tags:#pdf#OCR#docx#extraction#tables#document
One-click install
npx skills add https://github.com/JansenAnalytics/claudex --skill doc-reader-jansenanalytics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/JansenAnalytics/claudex/tree/main/skills/doc-reader
Command: npx skills add https://github.com/JansenAnalytics/claudex --skill doc-reader-jansenanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pdfplumber, python-docx, openpyxl, tabula-py, Pillow, beautifulsoup4, and includes scripts (resource) components.

What problem does it solve?

Reading and analysis of documents across formats is time-consuming and error-prone; this Skill automates text extraction, table parsing, OCR, and metadata generation to enable quick insights across PDFs, Word, Excel, images, and HTML.

Core Features & Use Cases

  • Text extraction from PDFs, DOCX, XLSX, images, and HTML with OCR fallback for scanned pages.
  • Table extraction and formatting in Markdown/CSV/JSON for downstream data processing.
  • Metadata extraction and document structure analysis to support indexing and search.

Quick Start

Ask the AI to extract text and tables from document.pdf and present a concise, structured summary.

Frequently Asked Questions about doc-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from a scanned PDF?▼

You can extract text and tables from a scanned PDF using OCR fallback with Tesseract, which recognizes image-based content and parses tables into Markdown, CSV, or JSON formats for downstream processing.

Can I extract structured data from DOCX and XLSX files in the same workflow?▼

Yes, you can extract structured data from DOCX and XLSX in the same workflow. It uses python-docx and openpyxl to pull text, tables, and metadata, delivering unified structured results suitable for indexing.

Does this PDF extraction method support metadata and document structure analysis?▼

Yes, this PDF extraction approach supports metadata and document structure analysis. It leverages PyMuPDF and pdfplumber to extract document properties and layout information, enabling effective indexing and search.

What is the best way to convert HTML documents to searchable text?▼

The best way to convert HTML to searchable text is using beautifulsoup4, which parses HTML structure to extract clean text content suitable for indexing and analysis workflows.

What are the limitations of OCR for table extraction in scanned documents?▼

OCR table extraction limitations in scanned documents include potential row and column misalignment, but the tool uses tabula-py with robust fallbacks to minimize errors and format tables accurately.

Related Skills

Explore More Education & Research Skills→
mfmezgermfmezger
5

convert-to-markdown

Convert PDF, DOCX, PPTX, XLSX, HTML, EPUB, and images to Markdown.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
LuYanFCPLuYanFCP

use-ocr

Extract text, tables, formulas, and handwriting from images and PDFs using local OCR tools.

Community
Intermediate