drive-documents

Extract text, metadata, and summaries from office documents and images.

1|Updated Dec 30, 2025

Search Tags:#documents #context #analysis #metadata #processing #drive

Ready to run

npx skills add https://github.com/statick88/dotfiles --skill drive-documents

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: drive-documents
Source: https://github.com/statick88/dotfiles/tree/main/amp/.agents/skills/drive-documents
Command: npx skills add https://github.com/statick88/dotfiles --skill drive-documents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, python-docx, pandas, openpyxl, python-pptx, Pillow, and includes scripts (resource) components.

What problem does it solve?

This skill automates the processing of various document types from local folders or Google Drive, extracting key information to build comprehensive project context.

Core Features & Use Cases

Multi-format Document Support: Handles PDFs, DOCX, XLSX, PPTX, TXT, images, and more.
Contextual Analysis: Extracts text, metadata, and summaries to enrich AI understanding.
Use Case: When onboarding a new project, use this skill to ingest all project-related documents from a designated Drive folder, providing the AI with a foundational understanding of the project's scope, content, and history.

Quick Start

Process all documents in the '/Users/statick/Documents/ProjectAlpha' folder to generate project context.

Frequently Asked Questions about drive-documents

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

FAQPage Schema

How do I extract text and metadata from PDF and DOCX files for project context?▼

To extract text and metadata from PDF and DOCX files for project context, this Skill processes local directories or Google Drive folders. It parses document content and metadata using Python libraries to provide foundational AI understanding.

Can I process images and PPTX presentations alongside XLSX spreadsheets?▼

Yes, you can process images and PPTX presentations alongside XLSX spreadsheets. The Skill supports multi-format document processing, extracting content and metadata from diverse office files and images using Pillow and python-pptx.

What Python libraries are required to parse Google Drive documents?▼

The Python libraries required to parse Google Drive documents include pypdf, python-docx, pandas, openpyxl, python-pptx, and Pillow. These dependencies handle diverse file parsing and image processing for context extraction.

What is the best way to ingest project documents for AI assistants?▼

The best way to ingest project documents for AI assistants is to process all files within a designated local or Drive folder. This extracts contextual information and metadata, building a comprehensive project foundation for the AI.

Does document processing for project context work with local directories?▼

Yes, document processing for project context works with local directories. The Skill automates extraction from local folders or Google Drive, pulling text and metadata from PDF, DOCX, XLSX, and TXT files to feed project context.