run-gauss

SkillDocs & knowledge

Acts as a knowledge base providing environment checklists, directory/scratch management, and bash command templates. USE WHEN you need to guide the execution of Gaussian computational chemistry jobs (.gjf) on local or remote/HPC environments.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the run-gauss skill

What this skill tells your AI

The instructions your AI receives, as published by jinzhezenggroup/computational-chemistry-agent-skills in quantum-chemistry/run-gauss/SKILL.md and read by ahel’s review.

Ask the user for these details

  • Run location: <local> or <remote/HPC> (and scheduler if any)
  • Environment setup: <env_setup_cmds> (e.g. module load / source script)
  • Gaussian executable: <gaussian_exec> (e.g. g16, g09, or absolute path)
  • Working directory:
    • local prep dir: <local_work_dir> (if applicable)
    • remote run dir: <remote_work_dir> (if applicable)
    • per-task dir: <task_work_dir>
  • Files:
    • input: <input.gjf>
    • Gaussian output: <gaussian_log>
    • wrapper stdout/stderr (if needed): <stdout_log>, <stderr_log>
  • Scratch:
    • GAUSS_SCRDIR=<scratch_dir> (e.g. ./scratch, $TMPDIR, or site-provided scratch)
    • whether to clean scratch after the run

Command template

<env_setup_cmds>
export GAUSS_SCRDIR=<scratch_dir>
mkdir -p "$GAUSS_SCRDIR"

<gaussian_exec> < <input.gjf> > <gaussian_log>

rm -rf "$GAUSS_SCRDIR"

Generate / assemble .gjf (when there is not an existing one)

Use gjf-flux to extract/assemble .gjf sections and build workflows.

Find the extract/assemble skill: gjf-flux

Submit via dpdispatcher (recommended)

Recommend using dpdispatcher to submit Gaussian calculations.

Find the submission skill: dpdisp-submit

Signals

GitHub stars
138
Forks
26
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
run-gauss
Source
github.com/jinzhezenggroup/computational-chemistry-agent-skills