agentsclimarketplace

Matminer toy property prediction starter

Skill ma-compbio-lab/SkillFoundry/skills/materials-science-and-engineering/matminer-toy-property-prediction-starter

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

Install
npx -y skills add ma-compbio-lab/SkillFoundry --skill matminer-toy-property-prediction-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.3 KB, 283 tokens by cl100k_base, as published. Nobody here has run it

Matminer Toy Property Prediction Starter

Use this skill to featurize a small composition table with matminer and fit a deterministic toy property predictor.

What it does

  • Loads a toy TSV of formulas and target values.
  • Uses matminer composition featurizers to build numeric features.
  • Fits a small scikit-learn regressor and summarizes training predictions plus feature importances.
  • Returns compact JSON suitable for materials-property-prediction starter workflows.

When to use it

  • You need a local starter for materials-property prediction.
  • You want a minimal example that connects composition featurization to a predictive model.

Example

slurm/envs/materials/bin/python skills/materials-science-and-engineering/matminer-toy-property-prediction-starter/scripts/run_matminer_toy_property_prediction.py \
  --input skills/materials-science-and-engineering/matminer-toy-property-prediction-starter/examples/toy_materials.tsv \
  --out scratch/materials/property_prediction_summary.json

Verification

  • Skill-local tests: python3 -m unittest discover -s skills/materials-science-and-engineering/matminer-toy-property-prediction-starter/tests -p 'test_*.py'
  • Repository smoke: python3 -m unittest tests.smoke.test_frontier_leaf_expansion_skills -v

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.