aqwa-batch-execution-deck-0-job-control-mandatory-for-all-runs
Sub-skill of aqwa-batch-execution: Deck 0 — Job Control (mandatory for all runs) (+3).
Best use case
aqwa-batch-execution-deck-0-job-control-mandatory-for-all-runs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of aqwa-batch-execution: Deck 0 — Job Control (mandatory for all runs) (+3).
Teams using aqwa-batch-execution-deck-0-job-control-mandatory-for-all-runs should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/deck-0-job-control-mandatory-for-all-runs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How aqwa-batch-execution-deck-0-job-control-mandatory-for-all-runs Compares
| Feature / Agent | aqwa-batch-execution-deck-0-job-control-mandatory-for-all-runs | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of aqwa-batch-execution: Deck 0 — Job Control (mandatory for all runs) (+3).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Deck 0 — Job Control (mandatory for all runs) (+3) ## Deck 0 — Job Control (mandatory for all runs) ``` SYSTEM DATA AREA 50000 ! Scratch memory allocation (bytes) JOB analysis LINE ! <jobname> <program_code> TITLE FPSO Diffraction Analysis 2026 NUM_CORES 8 ! OpenMP threads (base licence: max 4 free) OPTIONS REST AHD1 END ! REST=restart capable; AHD1=write ASCII .AH1 RESTART 1 1 ! Start stage, stop stage (1=LINE, 2=LIBR, 3=NAUT) ``` Common `OPTIONS` flags: | Flag | Effect | |------|--------| | `REST` | Enable restart capability (writes `.RES`) | | `AHD1` | Write ASCII hydrodynamic database (`.AH1`) for OrcaFlex import | | `GOON` | Continue past non-fatal errors | | `NOFIG` | Suppress figure output | | `NOLIST` | Suppress listing output | ## Deck Structure (Categories 1–6 for AQWA-LINE) | Category | Keyword | Purpose | |----------|---------|---------| | 0 | (top of file) | Job control (JOB, TITLE, NUM_CORES, OPTIONS, RESTART) | | 1 | `COOR` | Node coordinates: `ID X Y Z` | | 2 | `QPPL` / `TPPL` | Element topology: quad/tri panel connectivity | | 3 | `PMAS` | Mass properties | | 4 | `GEOM` | Geometric properties / CoG / inertia | | 5 | `GLOB` | Global environment (DPTH, DENS, ACCG) | | 6 | `FREQ` / `DIRN` | Wave frequencies and directions | | — | `STOP` | Terminates entire input file | ## Minimal AQWA-LINE DAT Template ``` SYSTEM DATA AREA 50000 JOB fpso LINE TITLE FPSO Hydrodynamic Diffraction NUM_CORES 8 OPTIONS REST AHD1 END RESTART 1 1 COOR 1001 0.0 0.0 0.0 1002 50.0 0.0 0.0 1003 50.0 15.0 0.0 1004 0.0 15.0 0.0 END QPPL QPPL DIFF 1001 1001 1002 1003 1004 END PMAS ... END GEOM ... END GLOB DPTH 200.0 DENS 1025.0 ACCG 9.81 END FREQ 0.2 0.3 0.4 0.5 0.6 0.8 1.0 1.2 1.5 2.0 END DIRN 0.0 45.0 90.0 135.0 180.0 END STOP ``` ## Critical DAT Conventions | Convention | Detail | |-----------|--------| | `QPPL DIFF` | Omitting `DIFF` makes panels non-diffracting — no error, wrong results | | `ILID AUTO 21` | Irregular frequency removal; add after ZLWL waterline card | | `SEAG nx ny` | 2 params in standalone mode; 6-param form is Workbench-only | | `OPTIONS GOON` | Overrides non-fatal errors; does NOT bypass FATAL mesh errors | | 80-col limit | Strictly enforced — AQWA truncates silently at column 80 | | `STOP` vs `END` | `STOP` terminates the whole file; `END` terminates each category |
Related Skills
digitalmodel-worktree-test-execution-with-shared-venv
Run digitalmodel tests from isolated worktrees without uv editable-dependency failures by using the main repo's existing virtualenv and PYTHONPATH.
plan-gated-issue-execution-wave
Execute a multi-issue architecture/planning wave in a plan-gated repo, then safely transition approved issues into implementation with file-based Codex prompts, local approval markers, subprocess monitoring, and cleanup handling for sandbox/hook edge cases.
work-around-merge-conflicts-in-test-execution
Run tests when repo has unresolved merge conflicts in config files by bypassing broken configs and executing tests directly
wave-based-parallel-plan-execution
Orchestrate phase execution by discovering dependencies, grouping into waves, spawning subagents, and collecting results with optional wave filtering
batch-syntax-repair-from-injection-errors
Detect and fix systematic syntax errors caused by line-injection scripts that split multiline constructs
batch-syntax-fix-with-regex-line-based-fallback
Fix repeated syntax errors across many files using regex, then fall back to line-based parsing when regex fails
batch-syntax-fix-regex-iteration
Iteratively fix widespread syntax errors across many files using regex refinement when initial patterns fail
batch-syntax-fix-pattern
Identify and repair cascading import/syntax errors across multiple files using regex-based line-scanning and verification
batch-regex-fix-import-syntax
Detect and fix mid-import blank-line syntax breaks across multiple files using line-based regex
plan-governance-vs-execution-boundary-for-adversarial-review
Keep stale-approval/governance remediation out of execution-path pseudocode, TDD, files-to-change, and deliverable acceptance when hardening a GitHub issue plan under adversarial review.
interactive-issue-execution-worktree-guardrails
Execute approved GitHub issues in isolated worktrees with interactive Codex/Codex runs, while containing agent drift and salvaging progress when provider/runtime problems occur.
gtm-prospect-pipeline-phased-execution
Phased execution pattern for