AI agent skills for scientific research
A library of validated agent skills and scientific databases that turns any AI agent into an AI scientist, compatible with multiple agent platforms.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Use instead of seed for a larger set of bioinformatics/life-science skills with strong BixBench accuracy.
197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.
A multilingual academic research skills library; drop-in replacement if you need grant-writing and broader academic coverage.
A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis.
A comprehensive research/engineering skills library; direct alternative for turning agents into research assistants.
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose for full automated scientific discovery via tree search instead of composing individual skills.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
A standalone automated discovery framework; use if you want a simpler all-in-one AI scientist, not a skill set.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Use for self-organizing agent teams running long experiments, instead of integrating skills manually.
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
A ready-to-run AI scientist implementation; choose if you want an autonomous agent rather than a skills library.
Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose for a medical-research-only subset of agent skills when you don't need the seed's broader science coverage.
Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing.