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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# ASE Relax Workflow (Subskill)
## Scope
This subskill prepares relaxation workflow tasks only.
It should generate:
- optimizer workflow script (`BFGS`/`FIRE` etc.)
- 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
1. relax workflow script/layout
1. optimizer/convergence summary
1. assumptions and unresolved choices
1. handoff note to `dpdisp-submit` if execution is requested
The line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_vfs6twytp7vbo2mb
GET https://markdownregistry.com/api/v1/resolve?ref=jinzhezenggroup/computational-chemistry-agent-skills/relax
GET https://markdownregistry.com/api/v1/blob/7ed5f03c55f64aae332f1d30a0fd5193e8b16b0deaee10c3d3a6c9867ace9bf9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
jinzhezenggroup/computational-chemistry-agent-skills · .github/skills/create-skill/SKILL.md · Create new Agent Skills following the agentskills.io specification. Use when the user wants to create, scaffold, or…
jinzhezenggroup/computational-chemistry-agent-skills · agent-workflow/agent-taskboard-manifest/SKILL.md · It is a specification for semantic workflows used by agents to plan, generate, formalize, summarize, and execute…
jinzhezenggroup/computational-chemistry-agent-skills · analysis/phonopy/SKILL.md · General phonon-workflow skill built around phonopy, independent of force backend. USE WHEN you need to prepare…
jinzhezenggroup/computational-chemistry-agent-skills · analysis/reacnetgenerator/SKILL.md · Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. Use when the user wants to…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/SKILL.md · Unified ASE router skill with a tree of subskills for static/relax/MD/NEB workflows and backend adapters (GPAW, MACE)…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-calculators/SKILL.md · Route ASE calculator-backend requests to adapter subskills based on backend choice. Use when ASE workflows need…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-calculators/gpaw/SKILL.md · Configure ASE GPAW calculator adapter settings for ASE workflows. Use when ASE workflow tasks require GPAW backend…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-calculators/mace/SKILL.md · Configure ASE MACE calculator adapter settings for ASE workflows. Use when ASE workflow tasks require MACE backend…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-workflows/SKILL.md · Route ASE atomistic workflow requests to task-specific subskills based on user intent. Use when the user asks for…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-workflows/md/SKILL.md · Prepare ASE molecular-dynamics workflow tasks with backend-agnostic controls. Use when the user needs…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-workflows/neb/SKILL.md · Prepare ASE NEB workflow tasks with backend-agnostic controls. Use when the user needs reaction-path optimization…
jinzhezenggroup/computational-chemistry-agent-skills · atomistic-workflows/ase/ase-workflows/static/SKILL.md · Prepare ASE static (single-point) workflow tasks with backend-agnostic workflow controls. Use when the user needs…
jinzhezenggroup/computational-chemistry-agent-skills · quantum-chemistry/dft-siesta/relax/SKILL.md · Prepare SIESTA geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the…
jinzhezenggroup/computational-chemistry-agent-skills · quantum-chemistry/dft-vasp/relax/SKILL.md · Prepare VASP geometry-relaxation input tasks from a user-provided structure and essential DFT settings. Use when the…
jinzhezenggroup/computational-chemistry-agent-skills · quantum-chemistry/dft-abinit/relax/SKILL.md · Prepare ABINIT geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the…
jinzhezenggroup/computational-chemistry-agent-skills · quantum-chemistry/dftbplus/relax/SKILL.md · Prepare DFTB+ geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the…
jinzhezenggroup/computational-chemistry-agent-skills · quantum-chemistry/dft-cp2k/relax/SKILL.md · Prepare CP2K geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the…
