Release MetaClaw benchmarks and skill bank on Hugging Face #26
Description
Hi @huaxiu 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2603.17187.
The paper page lets people discuss your paper and find artifacts about it. I noticed you've released the code for MetaClaw on GitHub, along with several interesting artifacts like the MetaClaw-Bench, AutoResearchClaw, and the pre-built Skill Bank.
Would you like to host these datasets on https://huggingface.co/datasets? Hosting on Hugging Face will give your work more visibility and enable better discoverability through metadata tags. It also allows researchers to easily load your benchmarks using the datasets library:
from datasets import load_dataset
dataset = load_dataset("aiming-lab/MetaClaw-Bench")Besides that, the dataset viewer allows people to quickly explore the instructions and trajectories directly in the browser. After they are uploaded, we can also link the datasets to the paper page so people can discover your work more easily.
If you're interested, you can find a guide on uploading datasets here.
Let me know if you need any guidance!
Kind regards,
Niels
ML Engineer @ HF 🤗