orcaflex-spec-audit

Audit, classify, and score OrcaFlex spec.yml files across the model library for quality, schema validity, and structure type categorization.

5 stars

Best use case

orcaflex-spec-audit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Audit, classify, and score OrcaFlex spec.yml files across the model library for quality, schema validity, and structure type categorization.

Teams using orcaflex-spec-audit 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

$curl -o ~/.claude/skills/spec-audit/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/engineering/marine-offshore/orcaflex/spec-audit/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/spec-audit/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How orcaflex-spec-audit Compares

Feature / Agentorcaflex-spec-auditStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Audit, classify, and score OrcaFlex spec.yml files across the model library for quality, schema validity, and structure type categorization.

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

# OrcaFlex Spec Library Audit

Audit and classify all `spec.yml` files in the OrcaFlex library. Scores quality (0-100), validates against `ProjectInputSpec` schema, and infers structural category from path and content signals.

## Usage

```bash
# Basic audit (YAML output)
uv run python scripts/audit_spec_library.py

# With HTML report
uv run python scripts/audit_spec_library.py --html benchmark_output/spec_audit.html

# Custom root directory
uv run python scripts/audit_spec_library.py --root docs/modules/orcaflex/library/templates
```

## Quality Scoring (0-100)

| Criterion | Points | Check |
|-----------|--------|-------|
| Schema valid | +30 | `ProjectInputSpec(**data)` passes |
| Has comments | +20 | Lines starting with `#` |
| Meaningful name | +15 | Not temp/single-char/digits-only |
| Meaningful description | +10 | Not "Extracted from...", not "generic", len >= 10 |
| No raw_properties | +15 | `environment.raw_properties` absent |
| Compact file | +10 | < 1000 lines |

## Category Inference

Priority order:
1. **Schema key**: `riser:` key -> riser, `pipeline:` key -> pipeline
2. **Path parts**: `tier2_fast` -> riser, `jumper` -> jumper, `training` -> training
3. **Model library prefix**: `a`=riser, `b`=drilling, `c`=mooring, `d-g`=installation, `h`=heavy_lift, `k`=wind_turbine, `l`=vessel, `m`=pipeline
4. **Metadata fallback**: `metadata.structure` field value

## Output

### YAML (`audit_results.yaml`)
```yaml
summary:
  total: 81
  avg_quality: 53.0
  schema_valid_count: 73
  by_category: {riser: 19, installation: 18, mooring: 10, ...}
specs:
  - path: library/templates/riser_catenary/spec.yml
    name: riser_catenary_template
    quality_score: 100
    schema_valid: true
    category: riser
    model_type: riser
    line_count: 108
```

### HTML Report
Single-page report with summary cards, per-category tables, color-coded quality scores (green >= 70, yellow 40-69, red < 40).

## Template Library

6 curated templates at `docs/modules/orcaflex/library/templates/`:

| Template | Source | Lines |
|----------|--------|-------|
| riser_catenary | tier2_fast/a01_catenary_riser | 108 |
| riser_lazy_wave | tier2_fast/a01_lazy_wave_riser | 188 |
| pipeline_installation | pipeline/.../24in_pipeline | 101 |
| mooring_buoy | model_library/c07_metocean_buoy | 763 |
| installation_subsea | installation/mudmat | 196 |
| installation_pull_in | model_library/d02_pull_in_analysis | 645 |

All templates score 100/100 quality and pass schema validation.

## References

- Audit script: `scripts/audit_spec_library.py`
- Tests: `tests/scripts/test_audit_spec_library.py`
- Template catalog: `docs/modules/orcaflex/library/templates/catalog.yaml`
- Audit results: `docs/modules/orcaflex/library/templates/audit_results.yaml`
- Schema: `src/digitalmodel/solvers/orcaflex/modular_generator/schema/root.py`

Related Skills

OrcaFlex Specialist Skill

5
from vamseeachanta/workspace-hub

```yaml

llm-wiki-audit-feedback-loop

5
from vamseeachanta/workspace-hub

Durable feedback loop for correcting llm-wiki pages without losing the correction to chat history. Use when (1) a human notices a wiki page is wrong, outdated, or contradicts a source, (2) processing the `audit/` inbox of a domain wiki, (3) reviewing what feedback has been resolved vs deferred, (4) needing to leave a comment on a specific text range that survives line- number drift. Implements the anchored-text audit file pattern from lewislulu/llm-wiki-skill, adapted for workspace-hub's domain-wiki layout under /mnt/local-analysis/llm-wiki/wikis/<domain>/. Extends the 5-op model (compile/ingest/query/lint) from research/llm-wiki with the missing `audit` op. Never silently delete feedback — rejected audits stay archived with rejection rationale.

orcaflex-reporting-fixture-proof-pattern

5
from vamseeachanta/workspace-hub

Build and extend fixture-backed OrcaFlex reporting proof paths in digitalmodel using stable metadata baselines, normalized HTML snapshots, and reusable reporting test helpers.

digitalmodel-orcawave-orcaflex-proof-workflows

5
from vamseeachanta/workspace-hub

Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.

pre-completion-cleanup-audit

5
from vamseeachanta/workspace-hub

Audit and dispose of session residue (orphan files, scratch dirs, sibling-repo state, locks, trash-stages) BEFORE claiming a task complete. Required gate before any agent says "all done", "task complete", or hands work back to user/orchestrator.

repo-mission-portfolio-audit

5
from vamseeachanta/workspace-hub

Audit the workspace-hub repo portfolio to extract each repo's mission, identify documentation gaps, and prioritize a plan/approval sequence with explicit LLM-wiki weighting for future issue triage.

provider-session-ecosystem-audit-and-exporters

5
from vamseeachanta/workspace-hub

Build and maintain cross-provider session-log audits for Codex, Codex, Hermes, and Gemini, including exporter design, normalization, and behavioral verification.

orcawave-orcaflex-readiness-audit

5
from vamseeachanta/workspace-hub

Audit the real readiness of digitalmodel OrcaWave/OrcaFlex spec-driven workflows by reconciling workspace-hub issues, source/tests, semantic-equivalence boundaries, and wiki synthesis gaps.

read-only-pre-implementation-audit

5
from vamseeachanta/workspace-hub

Systematic cross-check workflow to validate assumptions before TDD coding begins

digitalmodel-orcawave-orcaflex-workflow

5
from vamseeachanta/workspace-hub

Current-state workflow for navigating and extending digitalmodel OrcaWave/OrcaFlex capabilities across code, tests, issues, queue tooling, and licensed-machine boundaries.

provider-audit-bootstrap-and-path-classification

5
from vamseeachanta/workspace-hub

Fix provider-session ecosystem audit failures caused by source-checkout imports and over-aggressive symbolic-path classification.

orcawave-orcaflex-semantic-proof-wave-closeout

5
from vamseeachanta/workspace-hub

Close out an OrcaWave/OrcaFlex semantic-proof wave after a PR merges, split unrelated CI blockers, and seed the next semantic-proof issue wave without duplicating existing issues.