Skip to content

hotskills.dev

Not in the top 1,000 by GitHub stars

Zhonghao1995/agentic-swmm-workflow

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility

Operations Research

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`skills/skill-author/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-anywhere/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-builder/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-calibration/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-canada/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-climate/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-design-review/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-end-to-end/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-experiment-audit/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-gis/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-network/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-params/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-plot/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-report/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-runner/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-uncertainty/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

`skills/swmm-water-quality/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a3bf4f23469c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit a3bf4f23469cf4252955901176c86b9c94578963

31GitHub stars

0stars in 7 days

17skills in this repository

11commits in 30 days

Heat

1.5

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

skill-author skills/skill-author
swmm-anywhere skills/swmm-anywhere
swmm-builder skills/swmm-builder
swmm-calibration skills/swmm-calibration
swmm-canada skills/swmm-canada
swmm-climate skills/swmm-climate
swmm-design-review skills/swmm-design-review
swmm-end-to-end skills/swmm-end-to-end
swmm-experiment-audit skills/swmm-experiment-audit
swmm-gis skills/swmm-gis
swmm-network skills/swmm-network
swmm-params skills/swmm-params
swmm-plot skills/swmm-plot
swmm-report skills/swmm-report
swmm-runner skills/swmm-runner
swmm-uncertainty skills/swmm-uncertainty
swmm-water-quality skills/swmm-water-quality

How it works

Choose a skill

skill-author

When your agent uses it

Draft a well-formed new skill (a SKILL.md scaffold, optionally with scripts/references) from a described recurring need, for human review and approval. Use whenever a repeated workflow gap has no existing skill covering it, when someone wants to propose or create a new skill or capability, or when an agentic system detects a recurring problem that warrants a brand-new skill rather than editing an existing one. Domain-general — works for any modeling or workflow domain; SWMM is just one example.

What it loads into context

Frontmatter

106 tokens

Always available to the agent

SKILL.md

1,027 tokens

When the skill is activated

Reference documents

764 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

When to use
How to draft a skill
What makes a good skill
Output contract
Safety / boundaries

Scripts executed separately

scripts/validate_skill.py
tests/test_validate_skill.py

Files

SKILL.mdcore4,676 bytes
SKILL.mdcore4,676 bytes
SKILL.mdcore4,676 bytes
assets/SKILL.template.mddoc610 bytes
references/skill-format.mddoc2,693 bytes
scripts/validate_skill.pyruns4,358 bytes
tests/test_validate_skill.pyruns3,132 bytes

Read SKILL.md


# Skill author

Turn a description of a recurring need into a **draft skill** that a human can review and approve. This skill writes proposals; it never installs, activates, or edits skills on its own — a freshly drafted skill is a proposal, not a verified capability.

It is domain-general: nothing here is specific to stormwater or SWMM. The same recipe produces a skill for any modeling or workflow domain.

## When to use

- A recurring problem keeps showing up and **no existing skill covers it** — the gap itself is the trigger to propose a new one.
- Someone asks to "create / propose / draft a new skill" for some capability.
- An agentic system (e.g. a memory or lessons-learned layer) flags a repeated pattern that warrants a new skill rather than a tweak to an existing one.

If an existing skill already covers most of the need, **improve that one instead** — don't create a near-duplicate (see step 2).

View the complete source on GitHub

swmm-anywhere

When your agent uses it

Synthesize a plausible SWMM drainage network from public data (OSM streets + DEM) when NO real pipe-network data exists — input is just a bbox. Use ONLY when the user has no pipe shapefile/CAD/GIS data, or to establish a baseline before real data arrives; if real pipe data exists, route to swmm-network or swmm-gis instead.

What it loads into context

Frontmatter

85 tokens

Always available to the agent

SKILL.md

3,275 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill does
Required inputs
Optional inputs
Defaults — tuned for fewer, more useful outfalls
Adjusting the synthesis — orphan nodes, too many / too few pipes
Skill artifacts produced
Example invocation
What to do next
Constraints and known limits
Installing — and credit where it's due

Scripts executed separately

scripts/synth_from_bbox.py
tests/test_smoke.py
../swmm-network/scripts/network_qa.py
../swmm-network/scripts/network_qa.py

Files

SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
SKILL.mdcore12,499 bytes
scripts/synth_from_bbox.pyruns8,473 bytes
tests/test_smoke.pyruns2,323 bytes
../swmm-network/scripts/network_qa.pyruns7,728 bytes
../swmm-network/scripts/network_qa.pyruns7,728 bytes

Read SKILL.md


# swmm-anywhere

**Synthesize a plausible SWMM drainage network from public data (OSM streets + DEM) when no real pipe-network data exists.**

Use **ONLY** when the user explicitly does not have pipe shapefile / CAD / GIS data, or when establishing a baseline before real data arrives. **Do NOT use if `swmm-gis` or `swmm-network` can run on the user's actual data** — the synthesized network is an *inferred plausibility*, not measured infrastructure.

For bbox-only inputs without real pipe data: this is the right skill.
For inputs that include a `.shp`, `.csv`, or `network.json` of real pipes: route to `swmm-network` or `swmm-gis` instead.

## What this skill does

Given a bounding box (and optional region name), this skill:

1. **Downloads public source data** via SWMManywhere: OpenStreetMap streets, a DEM tile (Planetary Computer by default), building footprints, river lines.

View the complete source on GitHub

swmm-builder

When your agent uses it

Assemble a runnable SWMM INP deterministically from subcatchment geometry/attributes, merged parameter JSON, network JSON, and climate references. Use when creating auditable INP + manifest artifacts for downstream swmm-runner/calibration.

What it loads into context

Frontmatter

55 tokens

Always available to the agent

SKILL.md

1,850 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Contract
Inputs
Scripts
MCP
Smoke example
Water quality sections
Known limitations

Scripts executed separately

scripts/build_swmm_inp.py
../swmm-climate/scripts/format_rainfall.py
../swmm-climate/scripts/format_rainfall.py
../swmm-params/scripts/landuse_to_swmm_params.py
../swmm-params/scripts/landuse_to_swmm_params.py
../swmm-params/scripts/merge_swmm_params.py
../swmm-params/scripts/merge_swmm_params.py
../swmm-params/scripts/merge_swmm_params.py
../swmm-params/scripts/soil_to_greenampt.py
../swmm-params/scripts/soil_to_greenampt.py

Files

SKILL.mdcore6,951 bytes
SKILL.mdcore6,951 bytes
SKILL.mdcore6,951 bytes
SKILL.mdcore6,951 bytes
SKILL.mdcore6,951 bytes
examples/options_config.jsonasset605 bytes
examples/subcatchments_input.csvasset143 bytes
scripts/build_swmm_inp.pyruns70,271 bytes
../swmm-climate/scripts/format_rainfall.pyruns27,463 bytes
../swmm-climate/scripts/format_rainfall.pyruns27,463 bytes
../swmm-params/scripts/landuse_to_swmm_params.pyruns7,627 bytes
../swmm-params/scripts/landuse_to_swmm_params.pyruns7,627 bytes
../swmm-params/scripts/merge_swmm_params.pyruns5,320 bytes
../swmm-params/scripts/merge_swmm_params.pyruns5,320 bytes
../swmm-params/scripts/merge_swmm_params.pyruns5,320 bytes
../swmm-params/scripts/soil_to_greenampt.pyruns6,562 bytes
../swmm-params/scripts/soil_to_greenampt.pyruns6,562 bytes

Read SKILL.md


# SWMM Builder (INP assembly layer)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## Contract
Build a runnable SWMM `.inp` using explicit file inputs:
- `subcatchments.csv` (shape/area/outlet/routing basics)
- merged params JSON from `swmm-params`
- network JSON from `swmm-network`
- rainfall/time-series references from `swmm-climate`
- optional options config JSON

The builder writes:
- final SWMM INP text (`--out-inp`)

View the complete source on GitHub

swmm-calibration

When your agent uses it

Calibration and validation scaffold for EPA SWMM. Use when an agent needs to (1) compare simulated vs observed flow, (2) evaluate candidate parameter sets, (3) rank explicit candidates by an objective, (4) run a bounded random / LHS / adaptive search for the best-fitting parameters, (5) run a publication-grade SCE-UA calibration with KGE as the primary objective and (r, alpha, beta) decomposition reported, or (6) run a DREAM-ZS Bayesian calibration producing a posterior over parameters with Gelman-Rubin convergence checks. Dedicated sensitivity-analysis methods (OAT, Morris, Sobol') now live on the `swmm-uncertainty` skill.

What it loads into context

Frontmatter

150 tokens

Always available to the agent

SKILL.md

5,496 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

CLI verb: aiswmm calibrate (real engine)
What this skill provides
MCP tools
Scripts (Python implementations behind the MCP tools)
Expected workflow
Relationship to uncertainty analysis
Known limitations
Patch-map idea
Candidate parameter-set JSON idea
Search-space JSON idea
CLI examples
Candidate handover contract (issue #54)
Recommended near-term extensions

Scripts executed separately

scripts/candidate_writer.py
scripts/dream_zs.py
scripts/inp_patch.py
scripts/metrics.py
scripts/obs_reader.py
scripts/sceua.py
scripts/swmm_calibrate.py

Files

SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
SKILL.mdcore21,225 bytes
scripts/candidate_writer.pyruns17,416 bytes
scripts/dream_zs.pyruns25,240 bytes
scripts/inp_patch.pyruns2,274 bytes
scripts/metrics.pyruns5,956 bytes
scripts/obs_reader.pyruns5,232 bytes
scripts/sceua.pyruns16,499 bytes
scripts/swmm_calibrate.pyruns56,961 bytes

Read SKILL.md


# SWMM Calibration / Validation

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).


## CLI verb: aiswmm calibrate (real engine)

Since ADR-0005 the top-level verb drives this skill's SCE-UA engine directly:

```
aiswmm calibrate --inp model.inp --observed-csv observed.csv \
  --patch-map examples/calibration/patch_map.json \
  --run-id calib_001 --total-iters 200 \
  --param pct_imperv_s1=20,70 --run-dir runs/agent/calib_001 --progress

View the complete source on GitHub

swmm-canada

When your agent uses it

Fetch a ready-to-run SWMM model for any Canadian area from the SWMMCanada upstream service — real published municipal storm pipes where a supported city covers the AOI, synthesized elsewhere in Canada. Input is a bbox or GeoJSON polygon plus a rainfall date window. Use for Canadian locations; outside Canada route to swmm-anywhere instead. Documentation contract only — the runtime tool is the in-process fetch_swmm_from_canada; there is no script or MCP server in this skill.

What it loads into context

Frontmatter

106 tokens

Always available to the agent

SKILL.md

1,487 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill does
Required inputs
Optional inputs
Configuration
What to do next (the chain)
Boundaries

Files

SKILL.mdcore5,935 bytes

Read SKILL.md


# swmm-canada

**Fetch a ready-to-run SWMM model for a Canadian area from the SWMMCanada upstream service, then run, audit, calibrate, and force it in one canonical run folder.**

Use for any AOI inside Canada. The service auto-selects the build mode: **real published municipal storm networks** where a supported city covers the AOI (35 cities at the 2026-08 sync, e.g. Victoria, Ottawa, Toronto, Calgary, Vancouver, Regina), **synthesized** anywhere else in the country. Outside Canada, route to `swmm-anywhere` (global, synthesized).

This skill is a documentation contract: the implementation is the in-process typed tool `fetch_swmm_from_canada` (a pure-stdlib HTTP client, ADR-0001). There is no script directory and no MCP server here, and that is deliberate — the service boundary is HTTP, and the tool is already on the runtime's golden path.

## What this skill does

Given an AOI (bbox `[min_lon, min_lat, max_lon, max_lat]` or a GeoJSON Polygon string) and a rainfall date window (`start_date`, `end_date`, ISO dates):

1. **Announces a preview** (best effort): which mode and city the service will use.
2. **Submits the build** to the SWMMCanada tasks API and polls with live progress (network fetch, subcatchments, DEM, landcover/soil, climate, build).

View the complete source on GitHub

swmm-climate

When your agent uses it

Deterministic rainfall/climate formatting for SWMM. Use when converting timestamped rainfall CSV files into SWMM-ready [TIMESERIES] lines and [RAINGAGES] helper snippets for swmm-builder.

What it loads into context

Frontmatter

52 tokens

Always available to the agent

SKILL.md

2,026 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
Input CSV contract
SWMM `.dat` input contract
Scripts
Outputs
MCP
Example commands
Design storms
Known limitations

Scripts executed separately

scripts/build_raingage_section.py
scripts/design_storm.py
scripts/format_rainfall.py

Files

SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
SKILL.mdcore7,105 bytes
examples/rainfall_batch_rg1.csvasset134 bytes
examples/rainfall_batch_rg2.csvasset134 bytes
examples/rainfall_event.csvasset218 bytes
examples/rainfall_multi_station.csvasset290 bytes
scripts/build_raingage_section.pyruns5,898 bytes
scripts/design_storm.pyruns25,492 bytes
scripts/format_rainfall.pyruns27,463 bytes

Read SKILL.md


# SWMM Climate (MVP rainfall layer)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides
- Deterministic conversion from simple rainfall CSV to:
  - SWMM `[TIMESERIES]` text lines
  - structured JSON manifest for audit/provenance
- Deterministic helper generation for SWMM `[RAINGAGES]` section.
- MCP wrapper for agentic use.

## Input CSV contract
`format_rainfall.py` expects a header row and at minimum:
- `timestamp`: date-time string, default format `%Y-%m-%d %H:%M`

View the complete source on GitHub

swmm-design-review

When your agent uses it

Score a completed SWMM run against a configurable YAML rulebook of design checks — GB50014-style standards for real catchments, or the reference-free physical-plausibility rulebook for synthesized networks. Reads the run's existing manifest.json / model.rpt / model.inp and never re-runs SWMM. Use it post-run for compliance or plausibility review; continuity gating stays with postflight.

What it loads into context

Frontmatter

101 tokens

Always available to the agent

SKILL.md

1,661 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill does
CLI usage
Agent tool: `review_run`
Executed example
Return-period adequacy workflow
Metrics available today (PR1)
Output files
What the agent MUST say
What the agent MUST NOT say
Custom rulebooks
Part of

Scripts executed separately

scripts/design_review.py

Files

SKILL.mdcore6,512 bytes
SKILL.mdcore6,512 bytes
SKILL.mdcore6,512 bytes
rulebooks/gb50014_template.yamlasset8,108 bytes
rulebooks/synth_plausibility.yamlasset7,472 bytes
scripts/design_review.pyruns45,661 bytes

Read SKILL.md


# 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.

---

View the complete source on GitHub

swmm-end-to-end

When your agent uses it

Top-level orchestration skill for agentic SWMM modelling. Use when an agent needs one entrypoint that decides which module tools to run, in what order, and when to stop, for example to build, run, QA, and optionally calibrate a SWMM case from prepared or partially prepared inputs.

What it loads into context

Frontmatter

71 tokens

Always available to the agent

SKILL.md

5,997 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
Routing rule — real-data path vs synth-data path
When to use this skill
Recommended public memory preload
Supported operating modes
Required decisions before execution
Input completeness rules
Execution policy
Artifact handoff contract
Preflight
MCP execution notes
Agent prompt-level instruction
QA gates
Output contract
Recommended agent behavior
Known limitations

Scripts executed separately

../../scripts/install_mcp_deps.sh
../../scripts/install_mcp_deps.sh
../../scripts/install_mcp_deps.sh
../../scripts/install_mcp_deps.sh
../../scripts/install_mcp_deps.sh
../../scripts/migrate_audit_layout.py
../../scripts/real_cases/run_todcreek_minimal.py
scripts/mcp_stdio_call.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-experiment-audit/scripts/audit_run.py
../swmm-uncertainty/scripts/uncertainty_propagate.py
../swmm-uncertainty/scripts/uncertainty_propagate.py

Files

../../scripts/install_mcp_deps.shruns1,829 bytes
../../scripts/install_mcp_deps.shruns1,829 bytes
../../scripts/install_mcp_deps.shruns1,829 bytes
../../scripts/install_mcp_deps.shruns1,829 bytes
../../scripts/install_mcp_deps.shruns1,829 bytes
../../scripts/migrate_audit_layout.pyruns14,067 bytes
../../scripts/real_cases/run_todcreek_minimal.pyruns12,758 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
SKILL.mdcore24,312 bytes
scripts/mcp_stdio_call.pyruns5,679 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-experiment-audit/scripts/audit_run.pyruns93,064 bytes
../swmm-uncertainty/scripts/uncertainty_propagate.pyruns11,193 bytes
../swmm-uncertainty/scripts/uncertainty_propagate.pyruns11,193 bytes

Read SKILL.md


# SWMM End-to-End Orchestration

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides
- A top-level orchestration contract for the agent runtime.
- A stable handoff point for Agentic AI project memory in `memory/initial/`.
- A deterministic execution order across the existing module skills:
  - `swmm-canada` (entry skill for Canadian AOIs — real municipal pipes where covered, synthesized elsewhere in Canada)
  - `swmm-anywhere` (entry skill for data-scarce regions outside Canada — no real pipe data)
  - `swmm-gis`
  - `swmm-climate`
  - `swmm-params`
  - `swmm-network`

View the complete source on GitHub

swmm-experiment-audit

When your agent uses it

Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes. Use after any SWMM build/run/QA attempt, successful or failed, when an agent or CLI workflow needs a traceable record of inputs, commands, artifacts, metrics, QA checks, run-to-run differences, and first-user-friendly Obsidian visualization.

What it loads into context

Frontmatter

87 tokens

Always available to the agent

SKILL.md

1,961 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
When to use this skill
Output contract
CLI
Audit rules
Relationship to `swmm-end-to-end`
Obsidian support

Scripts executed separately

scripts/audit_run.py
scripts/init_obsidian_vault.py

Files

SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
SKILL.mdcore8,116 bytes
scripts/audit_run.pyruns93,064 bytes
scripts/init_obsidian_vault.pyruns8,128 bytes

Read SKILL.md


# SWMM Experiment Audit

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides

- A standard audit layer for Agentic SWMM runs.
- Consolidation of dispersed `manifest.json`, QA JSON, logs, metrics, and artifact paths.
- Machine-readable outputs for reproducibility and review.
- Obsidian-compatible Markdown notes for human research records.
- Default local Obsidian export into a clean English audit vault.
- Automatic update of the Obsidian `Experiment Audit Index`.
- Optional run-to-run comparison for baseline/scenario or before/after parser validation.

View the complete source on GitHub

swmm-gis

When your agent uses it

GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers. Use when the user asks to (1) delineate subcatchments through QGIS/GRASS (standard or entropy-guided), (2) preprocess QGIS-derived subcatchment polygons into builder-ready CSV, (3) identify high-entropy hotspot subcatchments, or (4) expose QGIS/GRASS-backed preprocessing as MCP tools for reproducible workflows. For bbox-only inputs WITHOUT real pipe data, use `swmm-anywhere` instead (it synthesises a plausible network from OSM streets + DEM).

What it loads into context

Frontmatter

134 tokens

Always available to the agent

SKILL.md

4,950 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Before calling any watershed delineation tool — ask the user
Choosing the right delineation mode
Entropy hotspot ranking
What this skill provides
Scripts
Sibling-skill script location
Known limitations
DEM-assisted example
QGIS data-prep example
QGIS/GRASS entropy-guided subcatchment example
Cell-level entropy/similarity aggregation diagnostic
MCP-facing operations
Notes

Scripts executed separately

scripts/area_weighted_swmm_params.py
scripts/basin_shp_to_subcatchments.py
scripts/find_pour_point.py
scripts/plot_qgis_standard_layers.py
scripts/preprocess_subcatchments.py
scripts/qgis_package_final_layers.py
scripts/qgis_prepare_swmm_inputs.py

Files

SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
SKILL.mdcore19,439 bytes
examples/qgis_overlay_subcatchments.geojsonasset1,275 bytes
examples/subcatchments_dem_assisted.geojsonasset832 bytes
examples/subcatchments_dem_stats_demo.jsonasset412 bytes
examples/subcatchments_demo.geojsonasset1,115 bytes
scripts/area_weighted_swmm_params.pyruns23,924 bytes
scripts/basin_shp_to_subcatchments.pyruns7,699 bytes
scripts/find_pour_point.pyruns4,639 bytes
scripts/plot_qgis_standard_layers.pyruns4,692 bytes
scripts/preprocess_subcatchments.pyruns30,357 bytes
scripts/qgis_package_final_layers.pyruns7,763 bytes
scripts/qgis_prepare_swmm_inputs.pyruns33,635 bytes

Read SKILL.md


# SWMM GIS / Preprocess

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## Before calling any watershed delineation tool — ask the user

When the user triggers watershed delineation (`qgis_raw_to_entropy_partition` or equivalent), **always ask these questions first** before making the tool call:

1. **Delineation mode** — Standard (fast, direct GRASS basins, no entropy) or Entropy-guided (paper WJE/NWJE/WFJS split-lump with sensitivity figures)?
2. **Stream threshold** — How many upslope cells define a stream? Default 100. Smaller = more streams = finer subcatchments.
3. **If entropy mode** — Delta threshold (default 0.015) and WFJS similarity threshold (default 0.95)? Use defaults unless doing sensitivity exploration.
4. **Purpose** — Planning / calibration exploration / sensitivity analysis / paper reproduction? This affects how strictly to apply paper-only splits and whether sensitivity figures are needed.
5. **CRS normalization needed?** — Are all input layers already in the same projected CRS? If uncertain, check first with `qgis_load_layers` + `qgis_validate_crs`.

View the complete source on GitHub

swmm-network

When your agent uses it

Network QA of an existing INP (disconnected nodes, missing outfalls, adverse or zero slopes) is one call, network_qa, so call it first. Also builds, validates and routes SWMM pipe-network models from raw municipal shapefiles or structured GIS/CAD exports. Use when handling junctions, conduits, outfalls, xsections, network field-mapping configs, or wiring subcatchments to upstream nodes. Requires real pipe data as SHP / GeoJSON / CSV — native CAD (DXF/DWG) is not parsed and must first be exported to one of these. For data-scarce areas where only a bbox is available and no pipe inventory exists, use `swmm-anywhere` instead.

What it loads into context

Frontmatter

157 tokens

Always available to the agent

SKILL.md

2,516 tokens

When the skill is activated

Reference documents

1,146 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
When to use this skill
MCP tools
Recommended orchestration
Templates and examples
Scripts (Python implementations behind the MCP tools)
Conventions
Known limitations

Scripts executed separately

scripts/_hash_util.py
scripts/assign_subcatchment_outlets.py
scripts/city_network_adapter.py
scripts/infer_outfall.py
scripts/inp_to_network.py
scripts/minimal_stub_network.py
scripts/network_import.py
scripts/network_qa.py
scripts/network_to_inp.py
scripts/prepare_storm_inputs.py
scripts/reorient_pipes.py
scripts/snap_pipe_endpoints.py

Files

SKILL.mdcore10,323 bytes
SKILL.mdcore10,323 bytes
examples/basic-network.jsonasset1,555 bytes
examples/city-dual-system/README.mddoc685 bytes
examples/city-dual-system/landuse.csvasset69 bytes
examples/city-dual-system/mapping.jsonasset1,941 bytes
examples/city-dual-system/outfalls.csvasset140 bytes
examples/city-dual-system/pipes.csvasset494 bytes
examples/city-dual-system/soil.csvasset66 bytes
examples/city-dual-system/subcatchments.csvasset145 bytes
examples/import-conduits.geojsonasset712 bytes
examples/import-junctions.geojsonasset465 bytes
examples/import-mapping.jsonasset1,305 bytes
examples/import-outfalls.geojsonasset267 bytes
scripts/_hash_util.pyruns826 bytes
scripts/assign_subcatchment_outlets.pyruns9,841 bytes
scripts/city_network_adapter.pyruns18,003 bytes
scripts/infer_outfall.pyruns6,656 bytes
scripts/inp_to_network.pyruns3,919 bytes
scripts/minimal_stub_network.pyruns4,422 bytes
scripts/network_import.pyruns8,489 bytes
scripts/network_qa.pyruns7,728 bytes
scripts/network_to_inp.pyruns4,202 bytes
scripts/prepare_storm_inputs.pyruns5,985 bytes
scripts/reorient_pipes.pyruns8,294 bytes
scripts/schema/network_model.schema.jsonasset4,640 bytes
scripts/snap_pipe_endpoints.pyruns8,012 bytes
templates/README.mddoc3,971 bytes
templates/city_mapping_raw_shapefile.template.jsonasset1,945 bytes

Read SKILL.md


# SWMM Network (pipe-system layer)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides

- A stable JSON schema for SWMM drainage-network structure.
- Two complementary import paths:
  - **Raw municipal shapefile path** (`prepare_storm_inputs` → `infer_outfall` → `reorient_pipes` → `import_city_network` → `qa`) for typical city storm-pipe + manhole layers that arrive as bare LineString shapefiles.
  - **Structured asset-DB path** (`import_city_network` directly, or `import_network` for a fully field-mapped GeoJSON/CSV) when the source already contains explicit from/to nodes, inverts, and diameters.
- A subcatchment-to-network wiring step (`assign_subcatchment_outlets`) that ensures surface runoff actually enters the pipe network at a real upstream junction rather than dumping straight to the outfall.
- Topology / hydraulic-attribute QA (`qa`).
- Lightweight introspection (`summary`).
- Export from network JSON to core SWMM INP sections (`export_inp`).

View the complete source on GitHub

swmm-params

When your agent uses it

Deterministic mapping from land use and soil texture to SWMM runoff/subarea and Green-Ampt infiltration parameters. Use when generating first-pass subcatchment parameter tables for swmm-builder.

What it loads into context

Frontmatter

47 tokens

Always available to the agent

SKILL.md

1,064 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
Scripts
Default lookup tables
Minimal input format
Outputs
CLI flags
MCP
Known limitations
Example commands

Scripts executed separately

scripts/landuse_to_swmm_params.py
scripts/merge_swmm_params.py
scripts/soil_to_greenampt.py

Files

SKILL.mdcore4,195 bytes
SKILL.mdcore4,195 bytes
SKILL.mdcore4,195 bytes
SKILL.mdcore4,195 bytes
SKILL.mdcore4,195 bytes
examples/landuse_input.csvasset96 bytes
examples/soil_input.csvasset74 bytes
references/landuse_class_to_subcatch_params.csvasset1,313 bytes
references/soil_texture_to_greenampt.csvasset363 bytes
scripts/landuse_to_swmm_params.pyruns7,627 bytes
scripts/merge_swmm_params.pyruns5,320 bytes
scripts/soil_to_greenampt.pyruns6,562 bytes

Read SKILL.md


# SWMM Params (MVP mapping layer)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides
- Transparent CSV-to-JSON mapping for:
  - land use class -> SWMM `[SUBCATCHMENTS]` + `[SUBAREAS]` defaults
  - soil texture/type -> SWMM `[INFILTRATION]` (Green-Ampt) defaults
- Deterministic, auditable outputs with explicit fallback usage and unmatched-key reporting.
- Optional merge step that emits one builder-ready JSON artifact.

## Scripts
- `scripts/landuse_to_swmm_params.py`
  - maps `subcatchment_id + landuse_class` to runoff/subarea parameters

View the complete source on GitHub

swmm-plot

When your agent uses it

Nature-spec figures from a SWMM run: paired rainfall (inverted) + node/link flow hydrograph (plot_run), network layout map (map_run), study-area map. 89/183 mm columns, 5-7 pt sans-serif, ticks out, no gridlines, Wong colour-blind-safe palette, vector PDF + 450 dpi PNG twin, SI units, no title; optional focus-day / HH:MM window crop. Use whenever an agent needs a publication-ready figure from a run's .inp + .out.

What it loads into context

Frontmatter

118 tokens

Always available to the agent

SKILL.md

3,217 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Before calling plot: ask the user
What this skill renders
Non-negotiables
Always do
Never do
Wong colour-blind-safe palette
Workflow
MCP tools
Known limitations

Scripts executed separately

scripts/plot_network_layout.py
scripts/plot_rain_runoff_si.py
scripts/plot_study_area.py
scripts/plot_style.py

Files

SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
SKILL.mdcore12,073 bytes
assets/nature.mplstyleasset4,262 bytes
scripts/plot_network_layout.pyruns26,288 bytes
scripts/plot_rain_runoff_si.pyruns24,084 bytes
scripts/plot_study_area.pyruns12,154 bytes
scripts/plot_style.pyruns6,948 bytes

Read SKILL.md


# SWMM Plot (Nature figure specification)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow): install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

Every figure this skill renders follows the Nature journal figure specification, the
project's standing figure standard. Source:
<https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/>.
The spec lives in exactly three places here, and the scripts hand-set nothing:

| File | Holds |
|---|---|
| [`assets/nature.mplstyle`](assets/nature.mplstyle) | the stylesheet (fonts, line weights, ticks, palette, TrueType text, constrained layout) |
| [`scripts/plot_style.py`](scripts/plot_style.py) | `apply_style()`, `figsize()`, `map_figsize()`, `save_figure()`, `legend_outside()`, the `WONG` palette |
| this file | the rules a figure must satisfy, and the tool contracts |

View the complete source on GitHub

swmm-report

When your agent uses it

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.

What it loads into context

Frontmatter

73 tokens

Always available to the agent

SKILL.md

1,671 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Purpose
CLI usage
Agent tool: `generate_report`
Executed example
Template override
Determinism contract
Scripts
Templates
Dependencies
Part of

Scripts executed separately

scripts/generate_report.py

Files

SKILL.mdcore6,327 bytes
SKILL.mdcore6,327 bytes
SKILL.mdcore6,327 bytes
scripts/generate_report.pyruns46,719 bytes
templates/default.yamlasset7,310 bytes

Read SKILL.md


# 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.

---

View the complete source on GitHub

swmm-runner

When your agent uses it

Run EPA SWMM (swmm5) simulations reproducibly and extract key metrics from the report file. Use when an agent needs to (1) run a .inp via swmm5 CLI, (2) generate a run directory with rpt/out + manifest, (3) extract peak flow/time for a node/outfall, (4) parse SWMM continuity (Runoff Quantity / Flow Routing) errors from .rpt, or (5) compare two .rpt files (e.g. GUI vs CLI) for equivalence.

What it loads into context

Frontmatter

118 tokens

Always available to the agent

SKILL.md

1,101 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What this skill provides
When to use this skill
MCP tools
Recommended orchestration
Conventions
Known limitations

Scripts executed separately

scripts/swmm_runner.py

Files

SKILL.mdcore4,087 bytes
SKILL.mdcore4,087 bytes
SKILL.mdcore4,087 bytes
SKILL.mdcore4,087 bytes
scripts/swmm_runner.pyruns20,714 bytes

Read SKILL.md


# SWMM Runner (CLI-first)

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## What this skill provides

- Deterministic execution wrapper around the `swmm5` binary.
- A standard **run directory** layout: `inp/`, `rpt/`, `out/`, `stdout`, `stderr`, `manifest.json`.
- Metric extraction read directly from SWMM's own `.rpt`:
  - peak flow + time-of-peak for any junction or outfall;
  - Runoff Quantity and Flow Routing continuity tables + continuity error %;
  - cross-run comparison (e.g. GUI vs CLI) on continuity error.

## When to use this skill

View the complete source on GitHub

swmm-uncertainty

When your agent uses it

Parameter and forcing uncertainty for EPA SWMM. Without observed flow, call propagate_parameter_ranges (global ranges, one SWMM run per sample, peak spread); the Morris/OAT/Sobol tools need an observed series. Use when an agent needs to (1) propagate parameter uncertainty through SWMM (fuzzy alpha-cut or Monte Carlo), (2) quantify hydrograph envelopes or output entropy without treating the run as calibration, (3) screen which parameters matter using OAT / Morris elementary-effects / Sobol' indices, (4) generate a rainfall ensemble (observed-series perturbation or IDF-curve design storms) and aggregate the resulting hydrograph envelope, or (5) build the integrated paper-reviewer-facing uncertainty source decomposition (`uncertainty_source_summary.md` + `uncertainty_source_decomposition.json`) over the raw outputs of the prior steps.

What it loads into context

Frontmatter

186 tokens

Always available to the agent

SKILL.md

5,257 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Agent path without observed data
What this skill provides
Scripts
Sensitivity-analysis sub-modes
Expected fuzzy workflow
Expected Monte Carlo / entropy workflow
Fuzzy Space
CLI Example
Outputs
Known limitations

Scripts executed separately

scripts/fuzzy_membership.py
scripts/parameter_recommender.py
scripts/rainfall_ensemble.py
scripts/sampling.py
scripts/sensitivity.py
scripts/source_decomposition.py
scripts/uncertainty_propagate.py
tests/test_fuzzy_membership.py
tests/test_sampling.py

Files

SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
SKILL.mdcore21,512 bytes
examples/fuzzy_space.jsonasset746 bytes
examples/rainfall_idf_config.jsonasset369 bytes
examples/rainfall_perturbation_config.jsonasset249 bytes
examples/uncertainty_config.jsonasset307 bytes
scripts/fuzzy_membership.pyruns12,244 bytes
scripts/parameter_recommender.pyruns12,236 bytes
scripts/rainfall_ensemble.pyruns39,274 bytes
scripts/sampling.pyruns6,178 bytes
scripts/sensitivity.pyruns19,296 bytes
scripts/source_decomposition.pyruns31,175 bytes
scripts/uncertainty_propagate.pyruns11,193 bytes
tests/test_fuzzy_membership.pyruns2,315 bytes
tests/test_sampling.pyruns1,623 bytes

Read SKILL.md


# SWMM Uncertainty

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

## Agent path without observed data

The honest split (live findings F-107 and F-109, 2026-09-03): WITH observed
flow, `swmm_sensitivity_oat` / `swmm_sensitivity_morris` / `swmm_sensitivity_sobol`
rank parameters against the data (they need an observed series and a patch
map). WITHOUT observed flow, `propagate_parameter_ranges` is the tool for both
questions: `mode=one_at_a_time` varies each parameter alone in one call and
returns a per-parameter spread and a ranking ("which parameters matter most");
the default `joint` mode samples all ranges together and reports the spread
("how uncertain is the peak"). Never emulate a ranking with one sweep per

View the complete source on GitHub

swmm-water-quality

When your agent uses it

Complete SWMM engine coverage: pollutant buildup/washoff simulation support and load reporting. Validate water-quality config JSON, build INPs with WQ sections, and extract pollutant load summaries from completed runs.

What it loads into context

Frontmatter

59 tokens

Always available to the agent

SKILL.md

2,043 tokens

When the skill is activated

Reference documents

1,280 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Purpose
Agent tool: `read_wq_loads`
WQ config JSON schema
Scripts
Executed examples
Validation constraints

Scripts executed separately

scripts/extract_wq_loads.py
scripts/validate_wq_config.py
tests/test_wq_builder_sections.py

Files

SKILL.mdcore6,594 bytes
SKILL.mdcore6,594 bytes
SKILL.mdcore6,594 bytes
SKILL.mdcore6,594 bytes
docs/rpt_wq_sections.mddoc5,071 bytes
scripts/extract_wq_loads.pyruns12,295 bytes
scripts/validate_wq_config.pyruns12,798 bytes
tests/test_wq_builder_sections.pyruns25,562 bytes

Read SKILL.md


# SWMM Water Quality Skill

## Purpose

Complete SWMM engine coverage for pollutant buildup/washoff simulation
and load reporting.  This skill provides:

1. `validate_wq_config.py` — validate a WQ config JSON before passing
   it to the builder.
2. `extract_wq_loads.py` — extract WQ load summaries from a SWMM RPT.

The water-quality sections (`[POLLUTANTS]`, `[LANDUSES]`, `[COVERAGES]`,
`[BUILDUP]`, `[WASHOFF]`, `[LOADINGS]`) are emitted by
`skills/swmm-builder/scripts/build_swmm_inp.py` via the

View the complete source on GitHub

Skills included

skill-author
swmm-anywhere
swmm-builder
swmm-calibration
swmm-canada
swmm-climate
swmm-design-review
swmm-end-to-end
swmm-experiment-audit
swmm-gis
swmm-network
swmm-params
swmm-plot
swmm-report
swmm-runner
swmm-uncertainty
swmm-water-quality

Repository facts

License: MIT
Created: Feb 26, 2026
Last pushed: Oct 28, 2026
Forks: 15
Open issues: 14
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 140 notes

skills/skill-author/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/skill-author/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-anywhere/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-network/scripts/network_qa.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-builder/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-builder/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-builder/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-builder/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-climate/scripts/format_rainfall.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-params/scripts/landuse_to_swmm_params.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-params/scripts/merge_swmm_params.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-params/scripts/merge_swmm_params.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/swmm-params/scripts/soil_to_greenampt.py:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
1 dangerous shell commandin 1 file: scripts/install_mcp_deps.sh:22
35 network referencesin 18 files: swmm-anywhere/scripts/synth_from_bbox.py:41 swmm-plot/SKILL.md:8 swmm-gis/scripts/qgis_package_final_layers.py:85 and 15 more
No hidden or obfuscated text
No instruction overrides
99 executable scriptsin 62 files: skills/swmm-experiment-audit/scripts/audit_run.py:1 scripts/install_mcp_deps.sh:1 skills/swmm-params/scripts/merge_swmm_params.py:1 and 59 more
6 references to secretsin 4 files: swmm-gis/scripts/qgis_prepare_swmm_inputs.py:41 swmm-runner/scripts/swmm_runner.py:60 swmm-gis/scripts/area_weighted_swmm_params.py:43 and 1 more
No requests to vote in Hot

Show all 141 signals by file

`scripts/install_mcp_deps.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Dangerous shell operationline 22
```
trap 'rm -f "$LOG"' EXIT
```

`scripts/migrate_audit_layout.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/real_cases/run_todcreek_minimal.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/skill-author/scripts/validate_skill.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/skill-author/tests/test_validate_skill.py`

Executable scriptline 1
```
Executable file
```

`skills/swmm-anywhere/SKILL.md`

Network accessline 165

This skill leans on **[SWMManywhere](https://github.com/ImperialCollegeLondon/SWMManywhere)**, a project from the Imperial College London team that figures out a plausible urban drainage network from OSM streets and a DEM. The clever part —

Network accessline 175

If you're publishing work that uses or builds on this skill, please **cite SWMManywhere** and check the upstream repository at <https://github.com/ImperialCollegeLondon/SWMManywhere> for their citation guidance and the BSD-3-Clause license

`skills/swmm-anywhere/scripts/synth_from_bbox.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 41

"Synthesize a plausible SWMM .inp from a bbox via SWMManywhere "             "(© Imperial College London, BSD-3-Clause, "             "https://github.com/ImperialCollegeLondon/SWMManywhere). "

Network accessline 42

"(© Imperial College London, BSD-3-Clause, "             "https://github.com/ImperialCollegeLondon/SWMManywhere). "             "Use only when no real pipe-network data exists for the area."

Network accessline 43

"https://github.com/ImperialCollegeLondon/SWMManywhere). "

Network accessline 178

file=sys.stderr,             )             print("      Upstream: https://github.com/ImperialCollegeLondon/SWMManywhere", file=sys.stderr)

Network accessline 179

)             print("      Upstream: https://github.com/ImperialCollegeLondon/SWMManywhere", file=sys.stderr)             print("      Install with:", file=sys.stderr)

Network accessline 180

print("      Upstream: https://github.com/ImperialCollegeLondon/SWMManywhere", file=sys.stderr)

`skills/swmm-anywhere/tests/test_smoke.py`

Executable scriptline 1
```
Executable file
```

`skills/swmm-builder/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-builder/scripts/build_swmm_inp.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-calibration/scripts/candidate_writer.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/dream_zs.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/inp_patch.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/metrics.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/obs_reader.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/sceua.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-calibration/scripts/swmm_calibrate.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-canada/SKILL.md`

Network accessline 53

The service URL comes from the `AISWMM_SWMMCANADA_URL` environment variable (a local container at `http://localhost:8000` or a hosted backend). `aiswmm doctor` probes `GET /api/v1/healthz` when the variable is set and reports reachability;

`skills/swmm-climate/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-climate/scripts/build_raingage_section.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-climate/scripts/design_storm.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-climate/scripts/format_rainfall.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-design-review/scripts/design_review.py`

Executable scriptline 1
```
Executable file
```

`skills/swmm-end-to-end/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-end-to-end/scripts/mcp_stdio_call.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-experiment-audit/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-experiment-audit/scripts/audit_run.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-experiment-audit/scripts/init_obsidian_vault.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-gis/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-gis/scripts/area_weighted_swmm_params.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 43
```
[Credential-related source omitted]
```

`skills/swmm-gis/scripts/basin_shp_to_subcatchments.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-gis/scripts/find_pour_point.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-gis/scripts/plot_qgis_standard_layers.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-gis/scripts/preprocess_subcatchments.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-gis/scripts/qgis_package_final_layers.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 85

if dr == 0 and dc == 0:                         continue                     nr, nc = r + dr, c + dc

Network accessline 86

continue                     nr, nc = r + dr, c + dc                     if (nr, nc) in stream_cells and not acc_arr.mask[nr, nc]:

Network accessline 87
```
nr, nc = r + dr, c + dc
```
Network accessline 96
```
_, nr, nc = max(candidates)
```

`skills/swmm-gis/scripts/qgis_prepare_swmm_inputs.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 41
```
[Credential-related source omitted]
```
Access to secretsline 82
```
[Credential-related source omitted]
```

`skills/swmm-network/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-network/scripts/_hash_util.py`

Executable scriptline 1
```
Executable file
```

`skills/swmm-network/scripts/assign_subcatchment_outlets.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/city_network_adapter.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/infer_outfall.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/inp_to_network.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/minimal_stub_network.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/network_import.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/network_qa.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/network_to_inp.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/prepare_storm_inputs.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/reorient_pipes.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-network/scripts/schema/network_model.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 3

"$id": "https://h2ox.me/schemas/swmm-network-model.schema.json",

`skills/swmm-network/scripts/snap_pipe_endpoints.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-params/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-params/scripts/landuse_to_swmm_params.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-params/scripts/merge_swmm_params.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-params/scripts/soil_to_greenampt.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-plot/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow): install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

Network accessline 10

Every figure this skill renders follows the Nature journal figure specification, the project's standing figure standard. Source: <https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/>.

Network accessline 11

project's standing figure standard. Source: <https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/>. The spec lives in exactly three places here, and the scripts hand-set nothing:

Network accessline 12

<https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/>.

Network accessline 39

| Rainfall (top, inverted) + node/link flow (bottom) hydrograph | `scripts/plot_rain_runoff_si.py` | `plot_run` tool, `aiswmm plot`, MCP `plot_rain_runoff_si` | `08_plot/fig_<node>_<attr>.png` + `.pdf` | | Network layout map (subcatchments,

Network accessline 41

| Study-area map (DEM hillshade, subcatchments, conduits, outfalls, scale bar, north arrow, cartouche) | `scripts/plot_study_area.py` | SWMMCanada fetch (`aiswmm canada`), or the script directly | `00_raw/study_area.png` + `.pdf` |

`skills/swmm-plot/assets/nature.mplstyle`

Network accessline 1

# Nature journal figure style for matplotlib, vendored for the swmm-plot skill. # Spec: https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/

Network accessline 2

# Spec: https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/

`skills/swmm-plot/scripts/plot_network_layout.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-plot/scripts/plot_rain_runoff_si.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-plot/scripts/plot_study_area.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-plot/scripts/plot_style.py`

Executable scriptline 1
```
Executable file
```

Network accessline 14

Spec: https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/

`skills/swmm-report/scripts/generate_report.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-runner/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-runner/scripts/swmm_runner.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 60
```
[Credential-related source omitted]
```
Access to secretsline 63
```
[Credential-related source omitted]
```

`skills/swmm-uncertainty/SKILL.md`

Network accessline 8

Part of [Agentic SWMM](https://github.com/Zhonghao1995/agentic-swmm-workflow) — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).

`skills/swmm-uncertainty/scripts/fuzzy_membership.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/scripts/parameter_recommender.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 119
```
[Credential-related source omitted]
```

`skills/swmm-uncertainty/scripts/rainfall_ensemble.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/scripts/sampling.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/scripts/sensitivity.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/scripts/source_decomposition.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/scripts/uncertainty_propagate.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Executable scriptline 1
```
Executable file; content unavailable
```
Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/tests/test_fuzzy_membership.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-uncertainty/tests/test_sampling.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-water-quality/scripts/extract_wq_loads.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-water-quality/scripts/validate_wq_config.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/swmm-water-quality/tests/test_wq_builder_sections.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 136 facts

Executable script in code of a file that runsscripts/install_mcp_deps.sh:1High confidence
Executable script in code of a file that runsscripts/install_mcp_deps.sh:1High confidence
Executable script in code of a file that runsscripts/install_mcp_deps.sh:1High confidence
Executable script in code of a file that runsscripts/install_mcp_deps.sh:1High confidence
Executable script in code of a file that runsscripts/install_mcp_deps.sh:1High confidence
Dangerous shell operation in code of a file that runsscripts/install_mcp_deps.sh:22High confidence
Executable script in code of a file that runsscripts/migrate_audit_layout.py:1High confidence
Executable script in code of a file that runsscripts/real_cases/run_todcreek_minimal.py:1High confidence
Executable script in code of a file that runsskill-author/scripts/validate_skill.py:1High confidence
Executable script in prose of a testskill-author/tests/test_validate_skill.py:1Low confidence
Network access in prose of the SKILL.mdswmm-anywhere/SKILL.md:165Low confidence
Network access in prose of the SKILL.mdswmm-anywhere/SKILL.md:175Low confidence
Executable script in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:1High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:41High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:42High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:43High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:178High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:179High confidence
Network access in code of a file that runsswmm-anywhere/scripts/synth_from_bbox.py:180High confidence
Executable script in prose of a testswmm-anywhere/tests/test_smoke.py:1Low confidence
Network access in prose of the SKILL.mdswmm-builder/SKILL.md:8Low confidence
Executable script in code of a file that runsswmm-builder/scripts/build_swmm_inp.py:1High confidence
Network access in prose of the SKILL.mdswmm-calibration/SKILL.md:8Low confidence
Executable script in code of a file that runsswmm-calibration/scripts/candidate_writer.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/dream_zs.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/inp_patch.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/metrics.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/obs_reader.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/sceua.py:1High confidence
Executable script in code of a file that runsswmm-calibration/scripts/swmm_calibrate.py:1High confidence
Network access in prose of the SKILL.mdswmm-canada/SKILL.md:53Low confidence
Network access in prose of the SKILL.mdswmm-climate/SKILL.md:8Low confidence
Executable script in code of a file that runsswmm-climate/scripts/build_raingage_section.py:1High confidence
Executable script in code of a file that runsswmm-climate/scripts/design_storm.py:1High confidence
Executable script in code of a file that runsskills/swmm-climate/scripts/format_rainfall.py:1High confidence
Executable script in code of a file that runsskills/swmm-climate/scripts/format_rainfall.py:1High confidence
Executable script in code of a file that runsswmm-climate/scripts/format_rainfall.py:1High confidence
Executable script in prose of a file that runsswmm-design-review/scripts/design_review.py:1Low confidence
Network access in prose of the SKILL.mdswmm-end-to-end/SKILL.md:8Low confidence
Executable script in code of a file that runsswmm-end-to-end/scripts/mcp_stdio_call.py:1High confidence
Network access in prose of the SKILL.mdswmm-experiment-audit/SKILL.md:8Low confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence
Executable script in code of a file that runsskills/swmm-experiment-audit/scripts/audit_run.py:1High confidence

and 86 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md skills/skill-author/SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.