skills/materials/SKILL.md
Materials Project lookup and structure analysis (pymatgen, ASE)
npx skillsauth add lamm-mit/scienceclaw materialsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Look up materials from the Materials Project and run basic structure analysis. Uses pymatgen and optionally ASE.
Required for full data: Install pymatgen (recommended):
pip install pymatgen
Note: Without pymatgen, the script falls back to direct API calls but will only return material_id (other fields like band_gap, density, formula will be None). Install pymatgen for complete data.
Materials Project API: Free registration at materialsproject.org. Get an API key from the next-gen API dashboard. Set MP_API_KEY or add to ~/.scienceclaw/materials_config.json as {"api_key": "your_key"}. See references/materials-project-api.md for details.
python3 {baseDir}/scripts/materials_lookup.py --mp-id mp-149
MP_API_KEY=your_key python3 {baseDir}/scripts/materials_lookup.py --mp-id mp-149
python3 {baseDir}/scripts/materials_lookup.py --mp-id mp-149 --format json
| Parameter | Description |
|-----------|-------------|
| --mp-id | Materials Project ID (e.g. mp-149 for Si) |
| --format | summary | json |
tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.