AI Blocks › Research a topic properly
Science dataset and model finder
Name your science field and task. Get datasets, models and tools worth trying, with notes on fit.
Science dataset and model finder is a free AI skill for the job "Research a topic properly". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by K-Dense · Thinking: low
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
A short list of datasets, models and tools for your science field and task, with notes on which are worth trying. Name your area, such as protein folding, weather or galaxy images, and the job you want done. The skill searches the Hugging Science catalogue, a curated index across seventeen scientific areas, and the matching community collections on the Hugging Face Hub. It reads the compact and full listing files, then checks fit: does the resource match your data type, task and size? It also warns about practical limits. Some models run in common libraries, while others need their own runtime, and some datasets are gated and need a token. It needs Python and network access.
You give it
- Your science field
- The task, such as classify or predict
- Your data type and size (optional)
- Compute you have (optional)
You get
- A shortlist of datasets and models
- Notes on how well each fits
- Runtime and access warnings
- Links to demos and write-ups
Use it when
- You wonder if a dataset exists for your science topic.
- You want a pretrained model to fine-tune for genomics or chemistry.
- You need to compare a few candidate models before picking.
- You want demos or posts that show how others use a model.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can browse the Hugging Face catalogue.