Data Hub Skills launch

We are excited to announce the launch of HistAI Data Hub Skills, a suite of tools designed to bridge the gap between advanced AI agents and large-scale pathology data.

This launch provides seamless integration for industry-leading agents, including Anthropic's Claude Code, Google's Gemini, and OpenAI's CODEX. By integrating these skills, developers and researchers can now grant their agents autonomous access to our extensive collection of more than 160,000 Whole Slide Images (WSIs), covering a diverse range of stains and clinical indications available in our CellDX Data Hub.

Autonomous Discovery and Retrieval

Traditionally, searching for specific pathology cases and managing cohorts has been a manual and time-consuming process. With HistAI Data Hub Skills, users can simply prompt their agents in plain English. For example:

"Find me all H&E slides for prostate acinar adenocarcinoma"

The agent will then autonomously search the database, identify appropriate cases, purchase the required cohort, and download both the high-resolution slides and their associated pathology reports. This significantly streamlines the development lifecycle for AI applications in pathology.

Open-Source Accessibility

The Skills repository is now publicly available on GitHub: github.com/HistAI/datahub.

For teams working with our open-source dataset, we are also ensuring compatibility with the broader ecosystem. You can access the dataset on Hugging Face and utilize the native Hugging Face Skills implementation, which is also compatible with all major agents: github.com/huggingface/skills.

By empowering modern AI agents with direct access to curated, high-quality pathology data, we are accelerating the future of computational pathology and making it easier than ever to build and deploy intelligent medical applications.