swmm-design-review

# swmm-design-review — Design Review / Code-Compliance Checker ## What this skill does Evaluates a completed SWMM run against a configurable rulebook of design checks. Reads the run's existing artifacts (manifest.json + model.rpt + model.inp) — SWMM is never re-run. Classifies each rule as `pass`, `fail`, `warn`, or `needs-data` and writes `11_review/design_review.json` + `11_review/design_review.md` into the run directory (canonical per ADR-0004; the underlying script's own bare default is the legacy `09_review/` — see *CLI usage* below). This skill is **decision-support only**. It never certifies regulatory compliance. --- ## CLI usage ```bash # Standalone script python3 skills/swmm-design-review/scripts/design_review.py \ --run-dir <path> # required: directory with model.rpt, manifest.json, model.inp [--rpt <path>] # override: explicit model.rpt path [--inp <path>] # override: explicit model.inp path [--manifest <path>] # override: explicit manifest.json path [--rules <rulebook>] # override rulebook YAML/JSON (repeatable for multiple books) [--out-dir <dir>] # bare-script default: <run-dir>/09_review/ (legacy) [--no-inp] # skip INP-derived metrics (slope, diameter) # CLI verb (registered in aiswmm CLI) — always passes --out-dir explicitly, # defaulting to the canonical <run-dir>/11_review/ (ADR-0004) aiswmm review --run-dir <path> [--rules <rulebook.yaml>] [--out-dir <dir>] ``` Ex...