Last commit on August 13, 2026·Created on May 28, 2026
K-Dense-AI/science-superpowers
“Composable computational-science methodology skills for AI research agents”
Combined rank
#519
across all skills
Stars
290
7d change unavailable
Forks
28
Watchers
2
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This collection provides a framework for implementing rigorous scientific workflows within AI agents. It prioritizes pre-registration and reproducible research pipelines over traditional development cycles, ensuring that agent-led investigations follow a structured scientific method.
The skills guide agents through the critical phases of research, from framing questions and designing analysis plans before data interaction to managing parallel investigations across independent datasets.
WHO IT'S FOR
AI agent / automation builders
implementing rigorous scientific workflows for agents
Computational scientists
standardizing reproducible research pipelines with AI
AI research engineers
scaling parallel investigations and simulations
Technical leads / architects
defining guardrails for AI-driven data analysis
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Claude Plugin · CLI Installer · Manual Copy · Symlink to AgentRepository instructions