skills.rest
InnerScopeHearing
InnerScopeHearingOFFICIAL
Explore all skills by this author →
GitHub

doc-indexer

Index documents from a document store into a full-text search catalog.

Updated May 30, 2026
Search Tags:#data extraction#full-text search#document management#document indexing#text classification
One-click install
npx skills add https://github.com/InnerScopeHearing/otchealth-claude-tools --skill doc-indexer-innerscopehearing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-indexer
Source: https://github.com/InnerScopeHearing/otchealth-claude-tools/tree/main/skills/doc-indexer
Command: npx skills add https://github.com/InnerScopeHearing/otchealth-claude-tools --skill doc-indexer-innerscopehearing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdf2text, libreoffice, tesseract, sqlite3, azure-document-intelligence, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill converts any document store into an organized, searchable archive, streamlining document management and retrieval processes.

Core Features & Use Cases

  • Document Extraction: Extracts text and structured data from various document formats, including PDFs, office documents, and images.
  • Cataloging: Generates a catalog of all documents, including metadata and classification.
  • Indexing: Builds a full-text search index for efficient retrieval.
  • Retrieval: Allows users to search and retrieve documents based on text, metadata, and classification.
  • Use Case: A CFO can use this Skill to index all financial documents stored in a company's data room, making it easy to find specific documents and extract key information.

Quick Start

Use the doc-indexer skill to index the documents in the 'financial_data_room' directory.

Frequently Asked Questions about doc-indexer

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

FAQPage Schema
How do I index a document store for full-text search across PDFs and office files?▼

Document indexing for full-text search converts PDFs, office documents, and images into a searchable archive by extracting text and building a catalog with metadata for efficient retrieval.

What's the best way to catalog and extract text from scanned images in a data room?▼

Text extraction from scanned images uses Azure Document Intelligence and Tesseract OCR to read image-based documents, cataloging them with metadata and classification for accurate document retrieval.

Do I need Azure services to extract structured data from PDF documents?▼

Azure services are required for OCR and Content Understanding during PDF data extraction, while Python libraries like pdf2text and libreoffice handle standard text parsing for document indexing.

Can I use SQLite for full-text search indexing in a legal document management system?▼

SQLite3 builds the full-text search index for legal and financial document management systems, enabling efficient retrieval of cataloged documents based on text, metadata, and classification.

Does this document indexing approach support extracting text from multiple office formats?▼

Document indexing supports multiple office document formats using libreoffice for parsing, extracting text and structured data to generate a comprehensive catalog with classification metadata.

How to retrieve specific financial documents after building a search index?▼

Document retrieval searches the generated full-text index using text, metadata, and classification filters to locate specific financial documents within an indexed data room archive.

Related Skills

Explore More Software Engineering Skills→
rysweetrysweet
72

pdf

Extracts text and tables from PDFs, creates, merges, and handles OCR for scanned documents.

Community
Advanced
alsk1992alsk1992
650

qmd

Search local Markdown notes with BM25, vector, and hybrid modes.

Community
Intermediate
SunS1eep1ngSunS1eep1ng

azure-ai

Access Azure AI services for search, speech, and document intelligence.

Community
Advanced
langbyyilangbyyi
96

pdf

Extract text, merge documents, fill forms, and OCR scanned PDFs.

Community
Intermediate