Hugging Science
A discovery layer for scientific ML on Hugging Face. When you're working on protein design, genomics, climate modeling, or any of 17 other science domains, this pulls from a curated catalog at huggingscience.co instead of making you grep through thousands of generic Hub entries. It maps your task to the right topic, fetches markdown indexes of datasets and models, then walks you through using them with standard HF libraries. The real value is curation: someone already filtered for quality and openness, so you're not comparing ESM2 variants or weather datasets from scratch. Includes interactive Spaces like BoltzGen for binder design. If your ML is scientific, start here before raw Hub search.
- skills.sh installs
- 1.9K
- GitHub stars
- 56.6K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add k-dense-ai/scientific-agent-skills --skill hugging-science --agent claude-codeInstalls into .claude/skills of the current project.
Files
Hugging Science
Hugging Science is a curated, LLM-friendly index of scientific datasets, models, blog posts, and interactive demos for ML researchers. Use it to find candidate resources, then verify their author documentation and scientific suitability; curation does not establish quality, openness, or executable compatibility.
There are two related surfaces, and you should use both:
- The catalog at
huggingscience.co— a static, parseable index of resources across 17 scientific domains. It exposesllms.txt(compact),llms-full.txt(full content), andtopics/<slug>.md(per-domain). These are markdown files designed to be fetched and read. - The
hugging-scienceHugging Face organization —huggingface.co/hugging-science— community-submitted datasets, models, and a changing collection of Gradio, Docker and static Spaces. Not every listing exposes an inference API.
The catalog points to resources hosted on the broader Hugging Face Hub. For example, ESM2 supports Transformers, while Evo2 requires its native runtime and OpenGenome2 needs explicit file-format handling. The catalog provides discovery; use each resource through its verified loader or service.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/k-dense-ai/scientific-agent-skills
- Categories
- Backend & APIs, Documentation, AI & Agent Building, Data Science & ML, Sales & Marketing, Design & UI/UX, Game Development
- First seen
- Jun 3, 2026
More from k-dense-ai/scientific-agent-skills
All 137- Autoskill1.9K
- Pdf1.8K
- Docx1.8K
- Pptx1.8K
- Exa Search1.8K
- Xlsx1.8K
- Iso 13485 Certification915
- Scientific Writing2.6K
- Scientific Visualization2.6K
- Scientific Critical Thinking2.5K
- Literature Review2.5K
- Scientific Brainstorming2.4K
- Statistical Analysis2.4K
- Paper Lookup2.4K
- Citation Management2.4K
- Peer Review2.3K
- Matplotlib2.3K
- Scientific Slides2.3K
- Scikit Learn2.3K
- Scientific Schematics2.3K
- Exploratory Data Analysis2.3K
- Statsmodels2.3K
- Markitdown2.2K
- Hypothesis Generation2.2K
Recommended
More Backend & APIs
digital-health-clinical-asr-setupnvidia/skillsStage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.1.9Kskills.sh installs
Premieresfkislev/flueControl Adobe Premiere Pro from the shell via Flue - ExtendScript bridges without an MCP server.1.9Kskills.sh installsdigital-health-clinical-asr-evalnvidia/skillsStage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).1.9Kskills.sh installstilegym-adding-cutile-kernelnvidia/skillsAdd a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and 1.9Kskills.sh installsHoudinisfkislev/flueControl SideFX Houdini from the shell via Flue - a Python bridge to hou without an MCP server.1.9Kskills.sh installs
meshy-3d-printingmeshy-dev/meshy-3d-agent3D print models generated with Meshy AI, plus Creative Lab consumer products. Handles slicer detection, white model printing, multi-color printing via API, the 1.9Kskills.sh installs