K-Dense-AI/scientific-agent-skills / skills/hugging-science
hugging-science
VerifiedDiscovers and evaluates scientific datasets, models, methodology posts, and Spaces through the Hugging Science catalog. Used when selecting scientific ML resources in biology, chemistry, genomics, materials, climate, physics, astronomy, medicine, mathematics, protein design, single-cell analysis, or PDE modeling, and when checking their actual datasets, Transformers, native-runtime, Inference Providers, or Gradio interfaces.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.5 KB |
| references/flagship-resources.md | markdown | 6.0 KB |
| references/review.md | markdown | 5.8 KB |
| references/topics-and-slugs.md | markdown | 4.5 KB |
| references/using-datasets.md | markdown | 5.1 KB |
| references/using-models.md | markdown | 6.7 KB |
| references/using-spaces.md | markdown | 5.2 KB |
| scripts/fetch_catalog.pyexecutable | script | 13.9 KB |
references/topics-and-slugs.md
View on GitHub# Topic slugs and entry schema
The Hugging Science catalog organizes scientific resources across **17 topics** in the 2026-10-01 public index (recheck when discovering resources). Each has a markdown file at `https://huggingscience.co/topics/<slug>.md`. Slugs are lowercase and hyphenated.
## Topic slugs and what each covers
| Slug | What's in here |
|---|---|
| `astronomy` | Galaxy/stellar surveys, cosmology, exoplanets, telescope imagery, foundation models for astronomical data |
| `benchmark` | Cross-domain evaluation suites — useful when comparing methods or running standard tests |
| `biology` | Protein/DNA/single-cell data and models, antibodies, bioacoustics, microbiome — broad biology umbrella |
| `biotechnology` | Synthetic biology, fermentation, applied genetic engineering data |
| `chemistry` | Molecules, reactions, drug discovery, SMILES corpora, DFT data, ligand-protein interactions |
| `climate` | Weather forecasting, climate models, atmospheric data, storm/flood prediction |
| `conservation` | Wildlife monitoring, biodiversity, camera-trap and bioacoustic models |
| `earth-science` | Remote sensing, satellite imagery, geospatial foundation models |
| `ecology` | Species distribution, ecosystem dynamics, biogeography (overlaps with conservation/biology) |
| `energy` | Battery materials, fusion plasma, grid simulation, renewables modeling |
| `engineering` | CAD, mechanical/structural simulation, robotics datasets |
| `genomics` | DNA language models, variant effect, single-cell, phylogenetics (overlaps heavily with biology) |
| `materials-science` | Crystal structures, band gaps, catalysts, perovskites, alloys, materials foundation models |
| `mathematics` | Theorem proving, formal math, mathematical reasoning datasets |
| `medicine` | Pathology, radiology, clinical NLP, drug-disease, EHR (overlaps with biology/chemistry) |
| `physics` | PDE solvers, fluid/plasma simulation, particle physics, physics-informed ML |
| `scientific-reasoning` | LLMs for scientific QA, paper understanding, multi-step scientific reasoning |
## Cross-domain reality
Most real tasks span multiple slugs. Pull all relevant ones rather than guessing:
- "Drug discovery" → `chemistry`, `biology`, `medicine`
- "Protein structure prediction" → `biology`, `chemistry`
- "Weather forecasting model" → `climate`, `earth-science`, `physics`
- "Single-cell foundation model" → `biology`, `genomics`, `medicine`
- "Battery electrolyte design" → `materials-science`, `chemistry`, `energy`
- "Bioacoustic species ID" → `biology`, `ecology`, `conservation`
When in doubt, fall back to `python scripts/fetch_catalog.py search "<keyword>"` against the full catalog.
## Entry schema
Each catalog entry is an H3 block with bulleted metadata followed by a description. Three flavors:
### Datasets
```
### org/dataset-name
- **Type**: <category, e.g. "Genomics", "Pathology", "PDE Simulation">
- **Tags**: <comma-separated topic tags>
- **HuggingFace**: https://huggingface.co/datasets/org/dataset-name
<one-line description>
```
### Models
```
### Model Display Name
- **Type**: <category, e.g. "Protein Language Model", "Materials Foundation Model">
- **Tags**: <comma-separated topic tags>
- **HuggingFace**: https://huggingface.co/org/model-id
<one-line description>
```
### Blog posts
```
### Post Title
- **Author**: <username>
- **Date**: <YYYY-MM-DD>
- **Tags**: <comma-separated>
- **Link**: <URL — usually huggingface.co/blog/...>
<one-line description>
```
## Endpoints
- `https://huggingscience.co/llms.txt` — compact site index
- `https://huggingscience.co/llms-full.txt` — every entry, every domain (this is the file to fetch when you want to grep across the whole catalog)
- `https://huggingscience.co/topics/<slug>.md` — one domain
- `https://huggingscience.co/feed.xml` — RSS for new entries
These are public unauthenticated GET resources, returning Markdown or RSS XML, without request bodies or pagination. The fetcher wraps the three Markdown routes; it does not parse the feed. `llms-full.txt` repeats resources across overlapping topic sections; `all` and `search` collapse repeated section/URL pairs after filtering. JSON output is a list of entry records (all fields are strings except `tags`, a string list), not an instruction channel. The index also includes compact bullet listings; structured parsing uses the H3 blocks in topic/full documents. The `fetch_catalog.py` script adds parsing, filtering, and JSON output. Prefer the script for structured access; use raw `WebFetch`/`curl` only if the script fails.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |