Check and work with local crystal structures

Open your own project in Codex or Claude Code, with permission to read and write files and run commands. An ordinary web chat may not be able to install a Skill.

• Codex or Claude Code with permission to read and write project files and run local commands. A chat page without file tools cannot install this skill.
• Python 3.11+ and uv. The upstream reviewed snapshot pins pymatgen 2026.9.24 and pymatgen-core 2026.9.23; check compatibility and preserve a project lock.
• Local structure checks do not need a Materials Project account. Its optional online queries need a separate request, network access, mp-api, and MP_API_KEY.

These requests run in your assistant's host environment. This page provides guidance; it does not run AI tasks or collect your project files.

Copy this request into your project conversation. Ask the assistant to review the original Skill and explain any required setup before using it.

I am using Codex or Claude Code with filesystem and shell tools. Please install pymatgen from https://github.com/K-Dense-AI/scientific-agent-skills at commit 593377bb048752abb0152deab9fbb1083a6087df, using skills/pymatgen. Read its SKILL.md and retrieve the complete skill with all referenced support files, including references, scripts, and assets when present; do not copy only SKILL.md. Preserve the original LICENSE.md and author attribution. Install it in the current project's skill directory supported by this host, following the project's existing configuration and without overwriting an existing skill. Check and explain required dependencies before making environment changes. Tell me where it was installed and how to invoke it in this host. Then wait for me to provide my files and task before running the workflow.

Once installation is confirmed, replace the example paths and details with your own files, then send this request in the same project.

Use the installed pymatgen skill to inspect my local structure.cif. Work locally and keep all Materials Project or other database queries off. Preserve the original CIF. Report parser warnings, composition, lattice parameters, coordinate mode, partial occupancy or disorder, and units. Check symmetry across a small, stated tolerance range and report how the result changes. Save a readable report, reproducible Python code, package versions, and any derived files in a new output folder. Do not silently correct or overwrite the source structure.

• A structure report covering composition, lattice, occupancy, parser warnings, and symmetry with stated tolerances.
• Reproducible Python code and provenance records; requested conversions or transformations are saved as new files.

Ask your assistant where each output was saved and how it was checked. Compare the result with your original inputs before you use or share it.

• Source and documentation checked on 2026-10-19; complete runtime workflows have not been tested here.
• Symmetry and parser results depend on tolerances, occupancies, and file quality. A successful parse does not prove a structure is physically correct.
• Materials Project access stays off by default. Database terms and third-party package licenses are separate from the skill's MIT license.

A third-party open-source selection by AimatraLab. The Skill belongs to its original author; source links go directly to their repository.

Original author

K-Dense Inc.

Repository

https://github.com/K-Dense-AI/scientific-agent-skills

Selected version

1.5

Fixed commit

593377bb048752abb0152deab9fbb1083a6087df

License

MIT

Documentation checked

2026-10-19