Open collection of 147 scientific skills for compatible AI agents.
This repository delivers 147 predefined skills that strengthen an AI agent's ability to perform multi-step scientific work. Skills cover sequence analysis, molecular docking, mass spectrometry, clinical trial data, medical imaging, and machine learning pipelines without requiring the agent to discover documentation on its own.
Agents activate the skills through the standard interface, gaining structured examples and domain context that improve reliability on tasks such as variant annotation, virtual screening, and EHR analysis. The collection works with any agent supporting the published Agent Skills format and remains fully open source under an MIT license.
Researchers, data scientists, and laboratory teams use the skills to accelerate routine analyses and prototype new workflows while keeping all execution local or on chosen compute resources.
Enable agents to run single-cell RNA-seq processing, phylogenetic tree construction, and variant annotation using documented steps and database connections.
Support molecular property prediction, docking simulations, and ADMET calculations with curated examples that guide the agent through each stage.
Assist with pharmacogenomics queries, trial matching, and medical image analysis by supplying structured pathways to relevant tools and datasets.
npx skills add K-Dense-AI/scientific-agent-skillsAny agent implementing the open Agent Skills standard, including Cursor, Claude Code, and similar tools listed in the repository.
Verified reviews from the community shape this listing's rating.
Loading reviews…
Data-driven comparisons, alternatives and rankings — kept current by our agents.
Featured in