Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

pymatgen Materials Analysis

A rigorous skill for validating, converting, and symmetry-analyzing crystal structures with current pymatgen APIs, plus offline phase diagrams and bounded Materials Project queries.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Safely ingests CIF/POSCAR/XYZ/JSON structures while capturing every parser warning, reporting units, occupancies, oxidation states, periodicity, and coordinate mode.
  • Sweeps symprec and angle_tolerance grids to produce a space-group sensitivity report instead of tuning tolerances until a preferred answer appears.
  • Plans representation loss before format conversion (selective dynamics, site properties, disorder) and only ever writes to a new path.
  • Builds strict, offline convex-hull phase diagrams from schema-validated computed energies; parses VASP vasprun.xml and writes/reads Q-Chem jobs.
  • Keeps Materials Project access dry-run by default; --execute allows one bounded summary query with recorded provenance, license, and citations.

Who it's for

  • DFT practitioners, computational materials graduate students, and materials data engineers.
  • Anyone who needs auditable provenance and parameters for publication-grade structure analysis.
  • Teams that want careful, quota-respectful Materials Project usage rather than bulk scraping.

Examples

  1. "Check whether this CIF triggers partial-occupancy or site-merging warnings" → runs composition_structure_validator.py structure structure.cif and reports warnings plus minimum interatomic distances.
  2. "How tolerance-sensitive is this structure's space group?" → symmetry_sensitivity_report.py structure.cif --symprec 0.001,0.01,0.1 --angle-tolerance 1,5.
  3. "Find on-hull phases in Li-Fe-O" → review the mp_query.py --chemsys Li-Fe-O dry-run plan, then approve --execute with an explicit output file.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/pymatgen/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/pymatgen folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pymatgen/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/pymatgen ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Install Python 3.11+ and uv.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/pymatgen ~/.claude/skills/
  4. In your project folder, pin dependencies: uv init --python 3.11, then uv add "pymatgen==2026.5.4" "pymatgen-core==2026.7.16" "mp-api==0.46.4", then uv sync --frozen.
  5. Restart Claude Code and ask something like "use the pymatgen skill to validate this CIF file".
  6. Only if you need Materials Project data, export MP_API_KEY in your shell or secret manager — never pass the key as a CLI argument.
View source on GitHub ↗License: MIT