jaechang-hits/SciAgent-Skills

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.

What it solves

AI coding agents often lack the deep, domain-specific knowledge required for complex life sciences tasks. SciAgent-Skills provides a massive library of structured scientific knowledge that allows these agents to perform bioinformatics, cheminformatics, and biostatistics tasks accurately without needing model fine-tuning.

How it works

The project consists of 199 self-contained markdown files (SKILL.md) that act as a knowledge base for AI agents. Each skill file contains runnable code examples, API guides, parameter settings, and troubleshooting steps. Agents like Claude Code, Cursor, or Windsurf read these files to understand how to use specific scientific tools and databases. It can be integrated as a plugin or by cloning the repository into a project directory where the agent can discover the skills via a registry file.

Who it’s for

It is designed for researchers and developers in computational biology, drug discovery, and proteomics who use AI coding agents to automate data analysis and scientific workflows.

Highlights

  • Extensive Library: Includes 199 skills across categories like Genomics, Structural Biology, Cell Biology, and Biostatistics.
  • Proven Performance: Boosted Claude Code's accuracy on the BixBench bioinformatics benchmark from 65.3% to 92.0%.
  • Broad Compatibility: Works with Claude Code, OpenAI Codex CLI, Cursor, and Windsurf.
  • Diverse Skill Types: Covers toolkits, database connectors, step-by-step pipelines, and conceptual guides.

Related

  • Project
    coreyhaines31/marketingskills

    A collection of AI agent skills that provide specialized marketing knowledge and workflows for tasks like SEO, copywriting, and conversion optimization.

  • Project
    K-Dense-AI/scientific-agent-skills

    A collection of 163 standardized skills for AI agents to perform complex scientific research workflows across biology, chemistry, medicine, and physics.

  • Project
    GPTomics/bioSkills

    bioSkills is a library of ready‑made code templates (“skills”) that teach LLM coding agents how to perform bioinformatics analyses—from sequence I/O to single‑cell, variant calling, structural biology, chemoinformatics, and workflow management. Installable via thin scripts for Claude Code, Codex, Gemini/Antigravity, OpenCode, and OpenClaw, the skills provide best‑practice command‑line flags, example scripts and usage guides, improving the correctness of AI‑generated bio‑informatics code.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills and workflows for AI agents to automate tasks ranging from content creation and 3D generation to complex software engineering.

  • Project
    NVIDIA-BioNeMo/bionemo-agent-toolkit

    A toolkit that provides AI agents with specialized skills to perform life science tasks like protein folding, molecular docking, and genomic analysis using NVIDIA's scientific libraries.