AC geospatial-data-quality-audit
Unified geospatial data quality audit for GIS data packages. Checks raster, vector, table, NetCDF, and directory structure. Outputs JSON/HTML reports, issue layers, checksums, and machine-readable exit codes. Use when the user wants to validate data packages, check delivery quality, find CRS/nodata/ geometry issues, or generate QA reports.
Unified geospatial data quality audit for GIS data packages.
As a process C 64/100 · Has gaps — weak spots: failures and branches, consistency, 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (geospatial-data-quality-audit) differs from the folder (geoskill-geospatial-data-quality-audit)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 26 steps
- 100Execution cost. Instruction body is 1021 tokens
- 100Running it twice. No mutating operations
- low 12 top-level sections: this looks like several domains in one skill
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)
- +2Single-language instructions
- +3Description length 341: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.