Scientific Agent Skills
177 scientific and research skills for AI agents -- bioinformatics, cheminformatics, clinical research, data analysis and scientific writing, plus 100+ databases.
- Actively maintained
- Permissive license
Overview
Scientific Agent Skills (formerly Claude Scientific Skills) is a library of procedural knowledge that turns a general coding agent into a research assistant. Its 177 skills teach the agent how to use specialized scientific libraries, databases and tools across biology, chemistry, medicine, physics, engineering, Earth science and data analysis -- for example single-cell RNA-seq, molecular docking, LC-MS/MS processing, satellite imagery or publication-quality figures. The collection is described in an arXiv paper (2609.00065).
It follows the open Agent Skills standard and works with Cursor, Claude Code, Codex, Google Antigravity and other compatible hosts. A fit for researchers and labs who want agents that follow validated scientific workflows rather than improvising them.
Why it's in this catalog
Catalog rating: ★★★★☆ (4/5)
By far the deepest domain-specific skill library; brings agent skills to scientific research, a use case no other project in this catalog covers.
- Emerging
- Vendor-backed
- Categories
- AI Agents & Agent Tools
- Languages
- Python, Shell
- License
- MIT
Related Projects
Anthropic Skills
Apache-2.0Anthropic's public repository of Agent Skills -- example skills, the Agent Skills specification and a starter template for teaching agents repeatable tasks.
Actively maintained
- AI Agents & Agent Tools
Hugging Face Skills
Apache-2.0Agent skills for AI/ML work on the Hugging Face Hub -- dataset creation, model training and evaluation, plus an hf CLI skill for core Hub operations.
Actively maintained
- AI Agents & Agent Tools
Agent Skills by Addy Osmani
MITProduction-grade engineering skills for AI coding agents, mapped to the development lifecycle -- spec, plan, build, test, review and ship.
Actively maintained
- AI Agents & Agent Tools
Superpowers
MITAn agentic skills framework that gives coding agents a full development methodology -- brainstorming, planning, TDD, debugging and subagent-driven execution.
Actively maintained
- AI Agents & Agent Tools
Spotted an error? Suggest an edit on GitHub.