TB2J Skill teaches an agent how to run and interpret the TB2J toolchain to compute magnetic interaction parameters such as Heisenberg exchange (J), Dzyaloshinskii–Moriya interaction (DMI), and anisotropy terms from DFT outputs (Wannier90, Siesta, Abacus). It maps common workflows, points to command references, and explains conventions and typical troubleshooting steps so the agent can advise users on preparing inputs, choosing the right conversion script, and interpreting outputs for simulation pipelines.
Use this skill when the user asks how to run TB2J commands, which script to use for a given DFT flavor (wann2J.py, siesta2J.py, abacus2J.py), how to prepare projection and spin settings, or when they need help debugging mismatches between computed and experimental interaction parameters. Also useful for non-collinear or spin–orbit cases and for exporting results to Vampire/Multibinit.
wann2J.py, siesta2J.py, abacus2J.py (references folder present)references/ describing flags, units, and expected filesBest matched to developer-focused agents with shell/CLI support (Copilot/Codex/Gemini CLI/Git-based agents) that can reason about scientific workflows and point users to repo references and commands.
This skill has not been reviewed by our automated audit pipeline yet.
