solver-benchmark-creating-benchmark-specs
Sub-skill of solver-benchmark: Creating Benchmark Specs.
Best use case
solver-benchmark-creating-benchmark-specs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of solver-benchmark: Creating Benchmark Specs.
Teams using solver-benchmark-creating-benchmark-specs 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/creating-benchmark-specs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How solver-benchmark-creating-benchmark-specs Compares
| Feature / Agent | solver-benchmark-creating-benchmark-specs | 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 solver-benchmark: Creating Benchmark Specs.
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
# Creating Benchmark Specs
## Creating Benchmark Specs
Use the standard DiffractionSpec YAML format:
```yaml
version: "1.0"
analysis_type: diffraction
vessel:
name: "MyHull_Benchmark"
type: "barge"
geometry:
mesh_file: "path/to/mesh.gdf"
mesh_format: gdf
symmetry: none
reference_point: [0.0, 0.0, 0.0]
waterline_z: 0.0
inertia:
mass: 1000.0 # kg
centre_of_gravity: [0.0, 0.0, -0.5]
radii_of_gyration: [1.0, 1.0, 1.0]
environment:
water_depth: 100.0
water_density: 1025.0
gravity: 9.80665
*See sub-skills for full details.*Related Skills
engineering-solver-domain-recon
Deep reconnaissance of an engineering solver domain (OrcaWave, OrcaFlex, CalculiX, OpenFOAM, etc.) across a multi-repo ecosystem — map infrastructure, issues, skills, data artifacts, machine constraints, and solver queue state before planning work.
orcawave-aqwa-benchmark
Cross-validation specialist for comparing OrcaWave and AQWA diffraction analysis results. Provides statistical comparison, peak value validation, and automated benchmark reporting for hydrodynamic coefficient verification.
hidden-folder-audit-specsarchive
Sub-skill of hidden-folder-audit: specs/archive/ (+1).
improve-creating-new-skills
Sub-skill of improve: Creating New Skills (+3).
solver-benchmark-solver-paths
Sub-skill of solver-benchmark: Solver Paths.
solver-benchmark-related-work-items
Sub-skill of solver-benchmark: Related Work Items.
solver-benchmark-programmatic-usage
Sub-skill of solver-benchmark: Programmatic Usage.
solver-benchmark-pre-flight-validation-checklist
Sub-skill of solver-benchmark: Pre-Flight Validation Checklist.
solver-benchmark-orcawave-via-orcfxapi
Sub-skill of solver-benchmark: OrcaWave (via OrcFxAPI) (+3).
solver-benchmark-multisolvercomparator
Sub-skill of solver-benchmark: MultiSolverComparator (+1).
solver-benchmark-mandatory-checks-before-committing-reports
Sub-skill of solver-benchmark: Mandatory Checks Before Committing Reports (+2).
solver-benchmark-correlation-thresholds
Sub-skill of solver-benchmark: Correlation Thresholds (+1).