Md

Skill jinzhezenggroup/computational-chemistry-agent-skills/quantum-chemistry/dft-siesta/md

Prepare SIESTA molecular-dynamics task inputs from a user-provided structure and MD controls. Use when the user needs finite-temperature trajectories with explicit ensemble, timestep, and thermostat controls.From its SKILL.md

Install

npx -y skills add jinzhezenggroup/computational-chemistry-agent-skills --skill md

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.2 KB, 173 tokens by cl100k_base, as published. Nobody here has run it

SIESTA MD (Subskill)

Scope

This skill prepares MD tasks only.

It should generate:

MD-capable SIESTA input
ensemble/integrator/thermostat controls
trajectory/output policy

It should not submit or execute jobs.

Must provide

structure input
basis/pseudopotential set choice
timestep and number of steps
ensemble intent (NVE/NVT/NPT)
temperature/pressure control policy

Usually should be explicit

initial velocity policy
output stride for energies/trajectory
charge/spin and SCF policy

Expected output

MD-task input layout
MD control summary and assumptions
unresolved choices for confirmation
handoff note to dpdisp-submit if execution is requested

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.