Marketplace for trusted AI agent skills

Skill Detail

Convert PDFs and document images into agent-ready Markdown with Docext

Run Docext locally or with a chosen model backend to turn PDFs and document images into structured Markdown for RAG, extraction, and review workflows.

Data Extraction & TransformationMulti-Framework
Data Extraction & Transformation Multi-Framework Security Reviewed
⭐ 2k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill convert-pdfs-and-document-images-into-agent-ready-markdown-with-docext Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
Python 3.11 environment, Docext package, source PDFs or document images, and a supported VLM backend such as vLLM, Ollama, or a configured hosted model provider
Install & setup
Create and activate a Python 3.11 virtual environment, install Docext from PyPI with pip install docext or uv pip install docext, configure the supported model backend required for the chosen workflow, then run the Docext PDF/image-to-Markdown interface or API described in the PDF2MD_README and EXT_README guides.
Author
Nanonets
Publisher
Organization
Last updated
Jul 1, 2026
Quick brief

Use Docext when an agent workflow needs document pages converted into structured Markdown before extraction, indexing, or human review. The operator installs the Python package, selects a supported local or hosted vision-language model backend, runs Docext against PDFs or images, and hands the resulting Markdown with tables, equations, signatures, watermarks, page numbers, and image descriptions to the downstream agent or RAG pipeline. Invoke this instead of using a hosted document product when the workflow needs a repeatable local/on-premises extraction step, model choice, or benchmarkable document-conversion behavior. The scope boundary is document-to-Markdown preparation for agent ingestion; it is not a generic Nanonets product listing, a full IDP platform card, or a broad document AI SDK reference.

How it works

What this skill actually does

Inputs and prerequisites: Python 3.11 environment, Docext package, source PDFs or document images, and a supported VLM backend such as vLLM, Ollama, or a configured hosted model provider.

Setup notes: Create and activate a Python 3.11 virtual environment, install Docext from PyPI with pip install docext or uv pip install docext, configure the supported model backend required for the chosen workflow, then run the Docext PDF/image-to-Markdown interface or API described in the PDF2MD_README and EXT_README guides.

Source and verification boundary: use https://github.com/NanoNets/docext/blob/main/PDF2MD_README.md as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.