HughYau/opensci-skill
A Meta-Skill for Building Agent Skills for Scientific Python Libraries
This project helps AI Agents accurately use specialized scientific Python libraries. It takes a scientific library's documentation and code as input and automatically generates a structured 'Skill' file. This 'Skill' file contains precise, up-to-date API signatures and usage examples, enabling AI Agents to correctly interact with libraries like MNE, PyMC, or scanpy without errors caused by outdated information or general language model knowledge. Data scientists, researchers, and engineers who build AI-powered assistants for scientific tasks would use this.
Use this if you need your AI Agent to accurately and reliably interact with specific, frequently updated scientific Python libraries for tasks like data analysis, simulation, or machine learning.
Not ideal if your AI Agent only needs to use general-purpose Python libraries or if you are not building an AI Agent that requires external knowledge injection.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/HughYau/opensci-skill"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
memodb-io/Acontext
Agent Skills as a Memory Layer
powroom/flins
Universal skill installer for AI coding agents
supabase/agent-skills
Agent Skills to help developers using AI agents with Supabase
DougTrajano/pydantic-ai-skills
This package implements Agent Skills (https://agentskills.io) support with progressive...
forefy/.context
AI Agent Skills for Smart Contract Auditing to generate triaged, industry grade report findings,...