Menu
Sub-skill of aqwa-batch-execution: Locating the Executable (+4).
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/vamseeachanta/workspace-hub --skill aqwa-batch-execution-locating-the-executableThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
Showing SKILL.md
Based on SOC occupation classification
| name | aqwa-batch-execution-locating-the-executable |
| description | Sub-skill of aqwa-batch-execution: Locating the Executable (+4). |
| version | 1.1.0 |
| category | engineering |
| type | reference |
| scripts_exempt | true |
# Find the AQWA executable (path varies by installation)
find /ansys_inc -name "Aqwa" -type f 2>/dev/null
# Typical Linux path (v2025 R1)
AQWA_EXE=/ansys_inc/v251/aqwa/bin/lnx64/Aqwa
# Confirm it exists and is executable
ls -la ${AQWA_EXE}
Directory is
lnx64on most installations. Verify on your site — may also belnamd64.
# Standard (fresh) run — program type determined by .DAT JOB card
${AQWA_EXE} std <jobname>
# Restart run (continue from previous stage)
${AQWA_EXE} restart <jobname>
<jobname> is the .DAT file base name without extension.
All output files are written to the working directory as <jobname>.*.
# Create a .com file listing jobnames, one per line
echo -e "stage1\nstage2\nstage3" > mylist.com
# Run all jobs in sequence
${AQWA_EXE} std mylist.com
${AQWA_EXE} std analysis
# Exit code is unreliable — check output files instead:
if grep -qi "error\|fatal\|abort" analysis.mes 2>/dev/null; then
echo "AQWA FAILED — check analysis.mes and analysis.lis"
exit 1
elif [ -f analysis.res ] && [ -f analysis.plt ]; then
echo "AQWA SUCCEEDED"
else
echo "AQWA INCOMPLETE — check analysis.mes"
exit 1
fi
#!/usr/bin/env bash
set -euo pipefail
AQWA_EXE=/ansys_inc/v251/aqwa/bin/lnx64/Aqwa
JOBNAME=${1:-analysis}
check_run() {
local job=$1
if grep -qi "error\|fatal" ${job}.mes 2>/dev/null; then
echo "FAILED: ${job}"; cat ${job}.mes; exit 1
fi
[ -f ${job}.res ] || { echo "FAILED: no .res for ${job}"; exit 1; }
echo "OK: ${job}"
}
echo "=== Stage 1: AQWA-LINE (diffraction) ==="
# JOB card in ${JOBNAME}.DAT must read: JOB analysis LINE
${AQWA_EXE} std ${JOBNAME}
check_run ${JOBNAME}
echo "=== Stage 3: AQWA-NAUT (time domain) ==="
# Separate .DAT with JOB card: JOB analysis NAUT + RESTART 3 3
cp ${JOBNAME}.dat ${JOBNAME}_naut.dat
# (edit RESTART record to 3 3 and JOB code to NAUT before running)
${AQWA_EXE} restart ${JOBNAME}_naut
check_run ${JOBNAME}_naut
echo "Pipeline complete."