Skills › Scientific Agent Skills › hugging-science › topics-and-slugs.md

topics-and-slugs.md

82 lines · skills/hugging-science/references/topics-and-slugs.md at 5f2bc03

Runs code

Most marks come from matching words in the file, so treat them as pointers.

1# Topic slugs and entry schema

3The 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 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.

Raw lines 1 to 4

5## Topic slugs and what each covers

7| Slug | What's in here |

8|---|---|

9| `astronomy` | Galaxy/stellar surveys, cosmology, exoplanets, telescope imagery, foundation models for astronomical data |

10| `benchmark` | Cross-domain evaluation suites — useful when comparing methods or running standard tests |

11| `biology` | Protein/DNA/single-cell data and models, antibodies, bioacoustics, microbiome — broad biology umbrella |

12| `biotechnology` | Synthetic biology, fermentation, applied genetic engineering data |

13| `chemistry` | Molecules, reactions, drug discovery, SMILES corpora, DFT data, ligand-protein interactions |

14| `climate` | Weather forecasting, climate models, atmospheric data, storm/flood prediction |

15| `conservation` | Wildlife monitoring, biodiversity, camera-trap and bioacoustic models |

16| `earth-science` | Remote sensing, satellite imagery, geospatial foundation models |

17| `ecology` | Species distribution, ecosystem dynamics, biogeography (overlaps with conservation/biology) |

18| `energy` | Battery materials, fusion plasma, grid simulation, renewables modeling |

19| `engineering` | CAD, mechanical/structural simulation, robotics datasets |

20| `genomics` | DNA language models, variant effect, single-cell, phylogenetics (overlaps heavily with biology) |

21| `materials-science` | Crystal structures, band gaps, catalysts, perovskites, alloys, materials foundation models |

22| `mathematics` | Theorem proving, formal math, mathematical reasoning datasets |

23| `medicine` | Pathology, radiology, clinical NLP, drug-disease, EHR (overlaps with biology/chemistry) |

24| `physics` | PDE solvers, fluid/plasma simulation, particle physics, physics-informed ML |

25| `scientific-reasoning` | LLMs for scientific QA, paper understanding, multi-step scientific reasoning |

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

Raw lines 5 to 26

27## Cross-domain reality

29Most real tasks span multiple slugs. Pull all relevant ones rather than guessing:

31- "Drug discovery" → `chemistry`, `biology`, `medicine`

32- "Protein structure prediction" → `biology`, `chemistry`

33- "Weather forecasting model" → `climate`, `earth-science`, `physics`

34- "Single-cell foundation model" → `biology`, `genomics`, `medicine`

35- "Battery electrolyte design" → `materials-science`, `chemistry`, `energy`

36- "Bioacoustic species ID" → `biology`, `ecology`, `conservation`

38When in doubt, fall back to `python scripts/fetch_catalog.py search "<keyword>"` against the full catalog.

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.

Raw lines 27 to 39

Runs code python scripts/fetch_catalog.py :38

40## Entry schema

42Each catalog entry is an H3 block with bulleted metadata followed by a description. Three flavors:

Entry schema

Each catalog entry is an H3 block with bulleted metadata followed by a description. Three flavors:

Raw lines 40 to 43

44### Datasets

45```

46### org/dataset-name

47- **Type**: <category, e.g. "Genomics", "Pathology", "PDE Simulation">

48- **Tags**: <comma-separated topic tags>

49- **HuggingFace**: https://huggingface.co/datasets/org/dataset-name

51<one-line description>

52```

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>

Raw lines 44 to 53

54### Models

55```

56### Model Display Name

57- **Type**: <category, e.g. "Protein Language Model", "Materials Foundation Model">

58- **Tags**: <comma-separated topic tags>

59- **HuggingFace**: https://huggingface.co/org/model-id

61<one-line description>

62```

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>

Raw lines 54 to 63

64### Blog posts

65```

66### Post Title

67- **Author**: <username>

68- **Date**: <YYYY-MM-DD>

69- **Tags**: <comma-separated>

70- **Link**: <URL — usually huggingface.co/blog/...>

72<one-line description>

73```

Blog posts

### Post Title
- **Author**: <username>
- **Date**: <YYYY-MM-DD>
- **Tags**: <comma-separated>
- **Link**: <URL — usually huggingface.co/blog/...>

<one-line description>

Raw lines 64 to 74

75## Endpoints

77- `https://huggingscience.co/llms.txt` — compact site index

78- `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)

79- `https://huggingscience.co/topics/<slug>.md` — one domain

80- `https://huggingscience.co/feed.xml` — RSS for new entries

82These 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.

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.

Raw lines 75 to 82