Docext

VERIFIED

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Downloads 0
Stars 2.0K
Version 1.0.0
Quality 98/100 · Excellent

Install with one command

$ npx skills add NanoNets/docext

Best for

Document processing

Find skills for parsing PDFs, extracting tables, running OCR, converting documents, and preparing file content for agent workflows.

Choose it when

  • You want a GitHub-backed skill with 2.0K stars.
  • You need a reusable install command for agents.
  • You want to compare it with related marketplace skills.

Check before install

  • Pushed 2mo ago
  • License: Apache-2.0
  • Review the repository README and examples.

Quality profile

Excellent candidate for agent workflows

High-confidence pick with strong adoption and healthy maintenance signals.

98
GitHub stars
2.0K
Freshness
2mo ago
Install ready
Yes
License
Apache-2.0

Workflow fit

Use this skill in these scenarios

Stack fit

Add it to a complete workflow

Overview

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Imported by the skill-only GitHub discovery pipeline because it matches agent skill, automation, RAG, or developer-tool signals. Protocol-server projects are excluded from automated imports.

Platform Compatibility

pythonFULL
ragFULL

Technical Details

Version
1.0.0
License
Apache-2.0
Last Updated
5/24/2026
Published
5/23/2026

Frameworks & Tools

PythonRAG