K-Dense-AI/scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard. observed · 2026-10-19
Health v2 · maintenance only
80/100
- Activity 100
- Release rhythm 86
- Longevity 26
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 0.0
- age_days: 366
- days_rel: 19
- days_push: 5
- n_releases_24m: 109
Adoption not part of the score
52679 stars · 4668 forks observed · 2026-10-19
What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.97
Scientific Agent Skills is a Python library that provides a collection of validated procedural skills and access to over 100 scientific databases for AI agents. It enables AI agents to perform complex research tasks across biology, chemistry, medicine, and more.
Use cases
- run bioinformatics analyses using an AI agent
- automate drug discovery pipelines with AI
- perform data analysis and visualization in scientific research
- enable an AI assistant to query and interpret scientific literature
- integrate AI agents with custom scientific databases
When to choose
- you need a ready‑made library of scientific procedures for AI agents
- you want to extend any Agent Skills‑compatible AI (Claude, Cursor, Codex, etc.)
- you prefer an open‑source, MIT‑licensed solution with extensive database coverage
When to avoid
- you require a standalone application rather than a library
- your project is not based on Python or does not support the Agent Skills standard
- you need real‑time low‑latency processing without external API calls
Facets
library · maturity active
agent-framework plugin-system data-science nlp artificial-intelligence bioinformatics python cross-platform agent-skills scientific-workflows procedural-knowledge open-agent-standard science chemoinformatics drug-discovery
10 sources
- readme: https://github.com/K-Dense-AI/scientific-agent-skills · fetched 2026-10-19 · 0a9694c5e0ba
- homepage: https://k-dense.ai · fetched 2026-08-29 · 1ada73af7833
- homepage: https://arxiv.org/abs/2609.00065 · fetched 2026-09-14 · 82c33415a715
- site_page: https://www.k-dense.ai/about · fetched 2026-08-29 · d2ae8a64ebdc
- site_page: https://www.k-dense.ai/docs · fetched 2026-08-29 · b19d8a17bdaf
- site_page: https://info.arxiv.org/about/donate.html · fetched 2026-09-14 · cca9c3a11c56
- site_page: https://info.arxiv.org/about/ourmembers.html · fetched 2026-09-14 · 10aa574961b4
- site_page: https://info.arxiv.org/about · fetched 2026-09-14 · a1f16f915a9a
- site_page: https://www.k-dense.ai/pricing · fetched 2026-08-29 · 447642fdaf5e
- site_page: https://www.k-dense.ai/faq · fetched 2026-08-29 · c2c243ce74d7
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| K-Dense-AI/scientific-agent-skills | main | 80 |
For agents
markdown · JSON · MCP: product_card(name="K-Dense-AI/scientific-agent-skills")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem