Computational-chemistry-agent-skills relax

Prepare ABINIT geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the user needs ion-only or cell-coupled structural optimization with explicit force/stress convergence controls.

install
source · Clone the upstream repo
git clone https://github.com/jinzhezenggroup/computational-chemistry-agent-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/quantum-chemistry/dft-abinit/relax" ~/.claude/skills/jinzhezenggroup-computational-chemistry-agent-skills-relax-06f121 && rm -rf "$T"
manifest: quantum-chemistry/dft-abinit/relax/SKILL.md
source content

ABINIT Relax (Subskill)

Scope

This skill prepares relaxation tasks only.

It should generate:

  • relaxation-capable ABINIT input
  • force/stress convergence controls
  • constraint policy when relevant

It should not submit or execute jobs.

Relax intent is mandatory

Before preparing inputs, classify intent:

  • ion-only relaxation
  • cell+ion relaxation
  • constrained relaxation (for example slab constraints)

If intent is ambiguous, ask for clarification.

Must provide

  • structure input
  • pseudopotential set choice
  • optimization and convergence thresholds
  • stress/cell relaxation policy when applicable

Usually should be explicit

  • fixed atom/layer constraints
  • charge/spin setup
  • cutoff/k-point/scf policy

Expected output

  1. relaxation-task input layout
  2. explicit relaxation-policy rationale
  3. settings summary and assumptions
  4. unresolved choices for confirmation
  5. handoff note to
    dpdisp-submit
    if execution is requested