hugging-science

Name: hugging-science
Author: K-Dense-AI

738installs3.1kforks

How to install hugging-science?

k-dense-ai/scientific-agent-skills/hugging-science

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill hugging-science

Installs into the current project.

Summary

Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving.

Files · 1

View on GitHub

SKILL.md

1	# Hugging Science
2
3	Hugging Science is a curated, LLM-friendly index of scientific datasets, models, blog posts, and interactive demos for ML researchers. Use it when a scientific ML question lands in front of you — it's much higher signal than generic search and the entries are pre-filtered for quality and openness.
4
5	There are two related surfaces, and you should use both:
6
7	- The catalog at `huggingscience.co` — a static, parseable index of resources across 17 scientific domains. It exposes `llms.txt` (compact), `llms-full.txt` (full content), and `topics/<slug>.md` (per-domain). These are markdown files designed to be fetched and read.
8	- The `hugging-science` Hugging Face organization — `huggingface.co/hugging-science` — community-submitted datasets, a few models, and ~27 interactive Spaces (notably BoltzGen for protein/binder design, Dataset Quest for submissions, and Science Release Heatmap for ecosystem visualization).
9
10	The catalog points to resources hosted on the broader Hugging Face Hub. So an entry like `arcinstitute/opengenome2` is a regular HF dataset that you load with the `datasets` library; an entry like `facebook/esm2_t33_650M_UR50D` is a regular HF model you load with `transformers`. The catalog's job is curation and discovery; usage goes through standard Hugging Face APIs.
11
12	## When to use this skill
13
14	Engage this skill when the user's task involves AI/ML applied to science. Common signals:
15
16	- Names a scientific domain (protein, genome, molecule, crystal, weather, climate, galaxy, EEG, microbiome, pathology, plasma, …)
17	- Asks "is there a dataset/model for X" where X is scientific
18	- Wants to fine-tune on scientific data, evaluate on scientific benchmarks, or reproduce a scientific ML paper
19	- Asks about specific known scientific models (Evo-2, ESM2, BoltzGen, Nucleotide Transformer, AlphaFold-derived, etc.)
20	- Needs an interactive demo for a scientific task (binder design, theorem proving, etc.)
21
22	If the task is generic ML (recommendation systems, chatbot RAG, vision on cats and dogs), this skill is not the right tool — defer to general HF Hub knowledge instead.
23
24	## Core workflow
25
26	Most invocations follow this five-step loop. Don't skip discovery — the value of Hugging Science is that it has already filtered hundreds of resources down to high-signal picks per domain.
27
28	### 1. Identify the domain(s)
29
30	Map the user's task to one or more of the 17 topic slugs:
31
32	`astronomy` · `benchmark` · `biology` · `biotechnology` · `chemistry` · `climate` · `conservation` · `earth-science` · `ecology` · `energy` · `engineering` · `genomics` · `materials-science` · `mathematics` · `medicine` · `physics` · `scientific-reasoning`
33
34	Some tasks span multiple topics (e.g., drug discovery → `chemistry` + `biology` + `medicine`). Fetch each relevant topic.
35
36	### 2. Fetch the relevant catalog content
37
38	Use the bundled script for clean, structured access:
39
40	```bash
41	python scripts/fetch_catalog.py topic biology
42	python scripts/fetch_catalog.py topic materials-science --filter models
43	python scripts/fetch_catalog.py search "protein language model"
44	python scripts/fetch_catalog.py all # full llms-full.txt
45	```
46
47	You can also fetch the raw markdown directly:
48
49	- `https://huggingscience.co/llms.txt` — compact index
50	- `https://huggingscience.co/llms-full.txt` — every entry, every domain
51	- `https://huggingscience.co/topics/<slug>.md` — one domain (slug is hyphenated, e.g. `materials-science.md`, `earth-science.md`, `scientific-reasoning.md`)
52
53	Each entry is a markdown block with `Type`, `Tags`, `HuggingFace` URL (or `Link` for blogs), and a one-line description. See `references/topics-and-slugs.md` for the entry schema and slug list.
54
55	### 3. Pick the right resource(s)
56
57	Read the descriptions and tags. Match to the user's task with judgment, not keyword overlap. Things to weigh:
58
59	- Scale fit — Evo-2 40B is overkill for a quick sequence classification on a laptop; ESM2 35M might be perfect.
60	- License and access — most are open, but check the underlying HF model card.
61	- Modality alignment — DNA vs. protein vs. SMILES vs. crystal structure; many "biology" models are not interchangeable.
62	- Recency / supersession — if both an older and newer entry cover the same task, prefer newer unless there's a reason not to.
63
64	If you're not sure which resource to pick, briefly present the top 2–3 candidates to

People who liked this also viewed

6 picks

Type

hugging-science

738installs3.1kforks

View on GitHub

How to install hugging-science?

k-dense-ai/scientific-agent-skills/hugging-science

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill hugging-science

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Hugging Science
2
3	Hugging Science is a curated, LLM-friendly index of scientific datasets, models, blog posts, and interactive demos for ML researchers. Use it when a scientific ML question lands in front of you — it's much higher signal than generic search and the entries are pre-filtered for quality and openness.
4
5	There are two related surfaces, and you should use both:
6
7	- The catalog at `huggingscience.co` — a static, parseable index of resources across 17 scientific domains. It exposes `llms.txt` (compact), `llms-full.txt` (full content), and `topics/<slug>.md` (per-domain). These are markdown files designed to be fetched and read.
8	- The `hugging-science` Hugging Face organization — `huggingface.co/hugging-science` — community-submitted datasets, a few models, and ~27 interactive Spaces (notably BoltzGen for protein/binder design, Dataset Quest for submissions, and Science Release Heatmap for ecosystem visualization).
9
10	The catalog points to resources hosted on the broader Hugging Face Hub. So an entry like `arcinstitute/opengenome2` is a regular HF dataset that you load with the `datasets` library; an entry like `facebook/esm2_t33_650M_UR50D` is a regular HF model you load with `transformers`. The catalog's job is curation and discovery; usage goes through standard Hugging Face APIs.
11
12	## When to use this skill
13
14	Engage this skill when the user's task involves AI/ML applied to science. Common signals:
15
16	- Names a scientific domain (protein, genome, molecule, crystal, weather, climate, galaxy, EEG, microbiome, pathology, plasma, …)
17	- Asks "is there a dataset/model for X" where X is scientific
18	- Wants to fine-tune on scientific data, evaluate on scientific benchmarks, or reproduce a scientific ML paper
19	- Asks about specific known scientific models (Evo-2, ESM2, BoltzGen, Nucleotide Transformer, AlphaFold-derived, etc.)
20	- Needs an interactive demo for a scientific task (binder design, theorem proving, etc.)
21
22	If the task is generic ML (recommendation systems, chatbot RAG, vision on cats and dogs), this skill is not the right tool — defer to general HF Hub knowledge instead.
23
24	## Core workflow
25
26	Most invocations follow this five-step loop. Don't skip discovery — the value of Hugging Science is that it has already filtered hundreds of resources down to high-signal picks per domain.
27
28	### 1. Identify the domain(s)
29
30	Map the user's task to one or more of the 17 topic slugs:
31
32	`astronomy` · `benchmark` · `biology` · `biotechnology` · `chemistry` · `climate` · `conservation` · `earth-science` · `ecology` · `energy` · `engineering` · `genomics` · `materials-science` · `mathematics` · `medicine` · `physics` · `scientific-reasoning`
33
34	Some tasks span multiple topics (e.g., drug discovery → `chemistry` + `biology` + `medicine`). Fetch each relevant topic.
35
36	### 2. Fetch the relevant catalog content
37
38	Use the bundled script for clean, structured access:
39
40	```bash
41	python scripts/fetch_catalog.py topic biology
42	python scripts/fetch_catalog.py topic materials-science --filter models
43	python scripts/fetch_catalog.py search "protein language model"
44	python scripts/fetch_catalog.py all # full llms-full.txt
45	```
46
47	You can also fetch the raw markdown directly:
48
49	- `https://huggingscience.co/llms.txt` — compact index
50	- `https://huggingscience.co/llms-full.txt` — every entry, every domain
51	- `https://huggingscience.co/topics/<slug>.md` — one domain (slug is hyphenated, e.g. `materials-science.md`, `earth-science.md`, `scientific-reasoning.md`)
52
53	Each entry is a markdown block with `Type`, `Tags`, `HuggingFace` URL (or `Link` for blogs), and a one-line description. See `references/topics-and-slugs.md` for the entry schema and slug list.
54
55	### 3. Pick the right resource(s)
56
57	Read the descriptions and tags. Match to the user's task with judgment, not keyword overlap. Things to weigh:
58
59	- Scale fit — Evo-2 40B is overkill for a quick sequence classification on a laptop; ESM2 35M might be perfect.
60	- License and access — most are open, but check the underlying HF model card.
61	- Modality alignment — DNA vs. protein vs. SMILES vs. crystal structure; many "biology" models are not interchangeable.
62	- Recency / supersession — if both an older and newer entry cover the same task, prefer newer unless there's a reason not to.
63
64	If you're not sure which resource to pick, briefly present the top 2–3 candidates to

People who liked this also viewed

6 picks

Type