← ClaudeAtlas

swmm-reportlisted

Generate a client-deliverable Word (.docx) report from an audited SWMM run directory. Reads manifest.json, experiment_provenance.json, model_diagnostics.json, comparison.json, and any PNG figures — SWMM is never re-run. Supports custom YAML/JSON section templates.
Zhonghao1995/agentic-swmm-workflow · ★ 11 · Data & Documents · score 72
Install: claude install-skill Zhonghao1995/agentic-swmm-workflow
# SWMM Report Export Skill ## Purpose Assemble a reproducible, client-deliverable Word (.docx) report from the artifacts produced by `swmm-experiment-audit` and `swmm-plot`. The script reads only existing files; it never re-runs SWMM or modifies the run directory. **Prerequisite:** the run directory must contain a `09_audit/` subdirectory with at least `experiment_provenance.json`. Run `aiswmm audit --run-dir <path>` first if that directory is absent. --- ## CLI usage ```bash # Standalone script python3 skills/swmm-report/scripts/generate_report.py \ --run-dir <path> # required: audited run directory [--out <path.docx>] # default: <run-dir>/report.docx [--template <path>] # YAML or JSON template (default: built-in) # CLI verb (registered in aiswmm CLI) aiswmm report --run-dir <path> [--out <path.docx>] [--template <template.yaml>] ``` Exit codes: `0` = success; `1` = missing dependency, missing audit dir, or template error; `2` = argument error. **python-docx dependency:** install with `pip install 'aiswmm[report]'`. The script exits immediately with a clear message if python-docx is absent. --- ## Agent tool: `generate_report` Registered in `AgentToolRegistry`. Direct handler (not MCP-routed) — shells out to `generate_report.py`, writes `<run-dir>/report.docx` (or the path supplied via `out`). ``` generate_report(run_dir="runs/my_run/") generate_report(run_dir="runs/my_run/", out="deliverables/run_report.docx") generate_report(ru