Calculate phase equilibria from a TDB database

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 3.12+, pycalphad 0.11.2, and NumPy for the upstream reviewed snapshot. Calculations use local files after setup.
• Real-material calculations need a suitable TDB with a separately checked license, assessment source, and valid temperature, pressure, and composition range.

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. Install pycalphad from https://github.com/K-Dense-AI/scientific-agent-skills at commit 593377bb048752abb0152deab9fbb1083a6087df, folder skills/pycalphad. Read SKILL.md and retrieve the complete skill with its references, scripts, and assets when present, not just the instruction file. Preserve the original repository LICENSE.md and K-Dense Inc. attribution. Use the current project's skill directory supported by this host, following existing project configuration. Do not overwrite an existing skill; explain conflicts first. Check dependencies and explain proposed environment changes before installing them. Tell me the installation path and how to invoke it, then wait for my files and task.

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 pycalphad skill for a local teaching demonstration with the bundled ideal-cu-ni.tdb: X(Ni)=0.5, pressure 101325 Pa, and temperatures 900, 1100, and 1300 K. Clearly label this as a hypothetical educational model, not an assessed Cu-Ni database or a real-alloy prediction. Inspect the elements and phases, state the mole-fraction basis, and explain the settings before calculating. Keep the original TDB and settings files unchanged. Save phase-equilibria CSV and a JSON report in a new output folder, inspect mass balance and the change on doubled sampling density, and report failed or uncertain checks openly. Do not download or substitute a commercial TDB.

• A CSV of stable phase compositions and molar phase fractions for each temperature and sampling run.
• A JSON report with database and settings hashes, excluded phases, mass-balance checks, sampling-sensitivity checks, and package versions.

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 2026-10-20; complete runtime workflows have not been tested here.
• The bundled Cu-Ni TDB is a hypothetical teaching model, not an assessed database. Its results must not be presented as predictions for real Cu-Ni metallurgy.
• The skill's MIT license does not grant rights to third-party thermodynamic databases. Check the actual TDB license and experimental assessment separately.
• Equilibrium depends on the selected database and phases. It does not predict precipitation kinetics, retained microstructure, or properties absent from that database.
• Mass-balance and sampling checks assess numerical behavior; passing them does not certify a global minimum or experimental validity.

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

1.1

Fixed commit

593377bb048752abb0152deab9fbb1083a6087df

License

MIT

Documentation checked

2026-10-20