Unified ASE router skill with a tree of subskills for static/relax/MD/NEB workflows and backend adapters (GPAW, MACE). Use when you need backend-agnostic workflow orchestration while keeping calculator-specific setup isolated in adapter subskills, with reproducible task preparation as output.
v0.1.0Requires Python and ASE. Optional backend dependencies are GPAW and/or MACE depending on selected adapter. Prepares tasks/configuration only; submit and run via dpdisp-submit when execution is requested.repositorysource
Please install the OpenClaw skill "ase" on the OpenClaw host.
Steps:
- Download: https://skills.computchem.cn/skill-zips/ase.zip
- Unzip it to get ase/
- Copy ase/ into the workspace skills directory (<workspace>/skills/)
- Start a NEW OpenClaw session so the skill is loaded
Then verify:
openclaw skills list --eligible
openclaw skills info ase
Prerequisites: Requires Python and ASE. Optional backend dependencies are GPAW and/or MACE depending on selected adapter. Prepares tasks/configuration only; submit and run via dpdisp-submit when execution is requested.
If you have shell access on the OpenClaw host, run the commands below.
·Direct download
# Download
wget -O ase.zip https://skills.computchem.cn/skill-zips/ase.zip
# Unzip. You will get a folder like:
# ase/
unzip ase.zip
# Copy into a loaded skills root:
# <workspace>/skills/ase/SKILL.md
mkdir -p <workspace>/skills
cp -r ase <workspace>/skills/
# Start a NEW OpenClaw session so the skill is loaded
# Verify:
openclaw skills list --eligible
openclaw skills info ase
Prerequisites: Requires Python and ASE. Optional backend dependencies are GPAW and/or MACE depending on selected adapter. Prepares tasks/configuration only; submit and run via dpdisp-submit when execution is requested.
ASE Top-Level Router
Use this skill as the unified entry point for ASE ecosystem tasks.
Purpose
This skill routes requests to one branch under the ASE tree:
ase/ase-workflows
ase/ase-calculators
Scope
This top-level router should:
decide whether the request is workflow-level or backend-adapter-level
gather the minimum context required for the selected branch
delegate details to the corresponding branch router
keep workflow logic and backend logic separated
This top-level router should not:
hardcode task-specific or backend-specific parameters directly
execute calculations directly
Routing rules
task intent is static/relax/md/neb workflow -> ase/ase-workflows
task intent is backend selection/configuration -> ase/ase-calculators
if mixed request, route to ase/ase-workflows first, then call ase/ase-calculators as dependency