Matminer Property Regression Starter

SkillAI & models

Use this skill to featurize simple formulas with Matminer and fit a deterministic toy regression model for materials-property prediction.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Matminer Property Regression Starter skill

About this capability

A framework for discovering, compiling, and validating reusable skills for scientific agents.

What this skill tells your AI

The instructions your AI receives, as published by ma-compbio-lab/skillfoundry in skills/materials-science-and-engineering/matminer-property-regression-starter/SKILL.md and read by ahel’s review.

Use this skill to featurize simple formulas with Matminer and fit a deterministic toy regression model for materials-property prediction.

What This Skill Does

  • converts formulas into composition features with Matminer
  • fits a small deterministic regression model
  • reports feature count, train fit quality, and holdout predictions

When To Use It

  • when a user asks for a starter on materials-property prediction
  • when you need a lightweight local template before connecting to a larger materials dataset
  • when you want a runnable example for the materials-property-prediction taxonomy leaf

Run

./slurm/envs/materials/bin/python skills/materials-science-and-engineering/matminer-property-regression-starter/scripts/run_matminer_property_regression.py --out scratch/materials/property_regression_summary.json

Notes

  • This is a toy local regression starter, not a benchmark-quality predictive model.
  • Pair it with larger curated datasets later if you need scientific performance claims.

Signals

GitHub stars
39
Forks
5
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
matminer-property-regression-starter
Source
github.com/ma-compbio-lab/skillfoundry