explaingit

k-dense-ai/scientific-agent-skills

23,671PythonAudience · researcherComplexity · 3/5LicenseSetup · moderate

TLDR

A collection of 135 pre-packaged skill instructions that teach your AI coding assistant how to use over 100 scientific databases and 70+ research Python packages, enabling reliable multi-step workflows in biology, chemistry, medical imaging, and more.

Mindmap

mindmap
  root((Scientific Skills))
    What it does
      AI agent skills
      Database access
      Research workflows
    Domains
      Biology genetics
      Drug discovery
      Medical imaging
      Materials science
    Tech stack
      Python
    Use cases
      Research automation
      Data analysis
      Grant writing
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Add biology or drug discovery skills to Claude Code so it can query PubChem or UniProt databases automatically

USE CASE 2

Run a multi-step genomics analysis workflow using an AI assistant that already knows the right Python packages

USE CASE 3

Enable your AI coding agent to search ClinicalTrials.gov and summarize trial data for a specific drug

USE CASE 4

Use the companion K-Dense BYOK desktop app as a full scientific research workspace without configuring individual skills manually

Tech stack

Python

Getting it running

Difficulty · moderate Time to first run · 30min

Requires configuring Claude Code or Cursor as your AI coding assistant plus API keys for the scientific databases you want to access.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

This repository is a collection of 135 ready-to-use "skills", pre-packaged instructions and examples, that you can add to an AI coding assistant to turn it into a scientific research helper. Instead of the AI having to figure out how to use complex scientific tools from scratch, these skills give it curated documentation and examples for over 100 scientific databases and 70+ Python packages commonly used in research. The skills cover a wide range of scientific domains: biology and genetics analysis, drug discovery and chemistry, medical imaging, clinical research, machine learning, materials science, physics, geospatial data, and more. For example, the skills give your AI agent direct access to databases like PubChem, UniProt, and ClinicalTrials.gov, along with guidance on how to use specialized tools for protein structure analysis, molecular simulation, and scientific writing. You would use this if you are a researcher, scientist, or anyone doing technical analysis who wants an AI assistant that reliably handles complex multi-step workflows, like processing genomics data, running drug screening analyses, or writing grant proposals. The skills work with AI coding tools including Claude Code and Cursor. The companion project K-Dense BYOK (bring your own API keys) is a desktop application built on top of these skills that provides a full research workspace. The README notes this repository is truncated, so the full README is longer than what was provided. The project is written in Python and released under an MIT license.

Copy-paste prompts

Prompt 1
I've added the k-dense-ai scientific-agent-skills to my Claude Code setup. Write a Python workflow that queries PubChem for a list of compound names and returns their molecular weights.
Prompt 2
Using the drug discovery skills from this repo, set up a Python pipeline that fetches target protein data from UniProt and filters by a specific disease area.
Prompt 3
I want to use the protein structure analysis skills. Walk me through installing the required Python packages and running a structure prediction on a sequence I provide.
Prompt 4
Help me use the clinical research skills to query ClinicalTrials.gov for active trials related to a specific drug name and output a summary table.
Prompt 5
How do I install and activate the scientific-agent-skills in Cursor so my AI assistant can handle genomics data analysis without extra prompting?
Open on GitHub → Explain another repo

← k-dense-ai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.