Ase workflows

Skill jinzhezenggroup/computational-chemistry-agent-skills/atomistic-workflows/ase/ase-workflows

Agent skills to run computational-chemistry tasks, used in OpenClaw

Install

npx -y skills add jinzhezenggroup/computational-chemistry-agent-skills --skill ase-workflows

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

What its author says it does

Copied from the file, not written here

Route ASE atomistic workflow requests to task-specific subskills based on user intent. Use when the user asks for ASE-based static, relaxation, MD, or NEB workflows and you must apply consistent workflow controls independent of calculator backend.

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

2.0 KB, as published. Nobody here has run it

ASE Workflows Router

Use this skill as the top-level ASE workflow orchestration layer.

Purpose

This skill routes requests to one task-specific workflow subskill path:

ase/ase-workflows/static
ase/ase-workflows/relax
ase/ase-workflows/md
ase/ase-workflows/neb

Scope

This router skill should:

classify user intent into one ASE workflow type
collect minimal task context (goal, convergence target, outputs)
delegate detailed workflow controls to selected subskill
request calculator backend via ase/ase-calculators router
enforce consistent output/handoff policy

This router skill should not:

hardcode backend-specific calculator parameters
execute or submit calculations directly

Routing rules

single-point energy/force/stress -> ase/ase-workflows/static
geometry optimization -> ase/ase-workflows/relax
finite-temperature trajectory -> ase/ase-workflows/md
reaction path / transition-state pathway -> ase/ase-workflows/neb

If intent is ambiguous, ask one focused clarification question.

Shared policy for all workflow subskills

separate workflow logic from backend adapter logic
expose assumptions and unresolved choices
return reproducible task layout and run script
if execution is requested, hand off to dpdisp-submit

Output from router

Provide:

selected workflow subskill path
why it was selected
missing minimum inputs (if any)
explicit next step (invoke selected subskill)