Relax
Skill jinzhezenggroup/computational-chemistry-agent-skills/atomistic-workflows/ase/ase-workflows/relax
Agent skills to run computational-chemistry tasks, used in OpenClaw
npx -y skills add jinzhezenggroup/computational-chemistry-agent-skills --skill relaxAssembled 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
Prepare ASE geometry-optimization workflow tasks with backend-agnostic controls. Use when the user needs structural relaxation while selecting optimizer, convergence target, constraints, and output trajectory policy independently 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
1.1 KB, as published. Nobody here has run it
ASE Relax Workflow (Subskill)
Scope
This subskill prepares relaxation workflow tasks only.
It should generate:
- optimizer workflow script (
BFGS/FIREetc.) - convergence policy (
fmax, max steps) - constraints and trajectory/log policy
Must provide
- structure input
- selected backend adapter
- optimizer choice
- force threshold and step limits
Usually should be explicit
- fixed-atom/layer constraints
- stress-aware relaxation policy
- restart behavior
Expected output
- relax workflow script/layout
- optimizer/convergence summary
- assumptions and unresolved choices
- handoff note to
dpdisp-submitif execution is requested