# docQA-skill

**Repository Path**: observerw/docQA-skill

## Basic Information

- **Project Name**: docQA-skill
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-06-05
- **Last Updated**: 2026-06-05

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# DocQA Skill

DocQA is a skill for indexing large PDF documents and answering questions with page-level evidence. It converts PDF pages into images, uses an OpenAI-compatible vision model to extract Markdown content, builds structured page indexes, and lets the agent retrieve relevant pages before answering.

## Prerequisites

- Linux or macOS
- Deno
- Poppler PDF tools, including `pdftoppm`
- An OpenAI-compatible vision model