AC swmm-gis
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).
GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 249): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4307 tokens
- 100Steps. 91 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (14 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -33 of 12 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 529: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 91 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.