inspect-geo
Skill31 starsChanged 8 months agoMITView on GitHub
Inspect any raster or vector geospatial file. Returns CRS, bounds, bands, resolution, dtype, attribute summaries, and band statistics. Supports GeoTIFF, Shapefile, GeoJSON, GeoPackage, GeoParquet, and more.
In this repository7 other files it gives its agents.
- detect-objectsSkill
- download-dataSkill
- install-geoaiSkill
- overture-dataSkill
- process-rasterSkill
- read-memoriesSkill
- search-stacSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Follow these steps in order, stopping and reporting clearly if any step fails.
- Very specific: line 20
If $0 looks like an absolute path, use it directly.
- Distinctive: line 37
If the extension is ambiguous, try raster first, then vector.
- Very specific: line 101
If STATE_DIR is set, update it with the inspected file info:
- Distinctive: line 122
If no state directory exists yet, skip this step silently.
- Distinctive: line 126
After reporting, briefly mention:
- Distinctive: line 131
Keep suggestions brief and show them only once.
- Very specific: line 135
If python3 is not found or import geoai fails, delegate to /geoai-skills:install-geoai.
- Distinctive: line 136
If rasterio or geopandas fails to read the file, try the GDAL/OGR fallback:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are helping the user inspect a geospatial data file.
Filename given: $0
Question: ${1:-describe the data}
Follow these steps in order, stopping and reporting clearly if any step fails.
Step 1 -- Resolve the file path
If $0 looks like an absolute path, use it directly. Otherwise search for it:
find "$PWD" -name "$0" -not -path '*/.git/*' 2>/dev/null- Zero results -> tell the user the file was not found and stop.
- More than one result -> list all matches, ask the user to re-run with a fuller path, and stop.
- Exactly one result -> use that full path as
RESOLVED_PATH.
Step 2 -- Classify the file type
Determine whether the file is raster or vector based on its extension:
- Raster:
.tif,.tiff,.img,.jp2,.vrt,.nc,.hdf - Vector:
.geojson,.json,.shp,.gpkg,.parquet,.geoparquet,.fgb,.kml
If the extension is ambiguous, try raster first, then vector.
Step 3 -- Run the appropriate inspection
Raster files
python3 -c "
import geoai
info = geoai.get_raster_info('RESOLVED_PATH')
for k, v in info.items():
print(f'{k}: {v}')
print('---')
print('Band Statistics:')
stats = geoai.get_raster_stats('RESOLVED_PATH')
for k, v in stats.items():
print(f'{k}: {v}')
"Vector files
python3 -c "
import geoai
info = geoai.get_vector_info('RESOLVED_PATH')
for k, v in info.items():
print(f'{k}: {v}')
"Replace RESOLVED_PATH with the actual absolute path before running.
Step 4 -- Answer the user's question
Using the metadata retrieved in Step 3, answer:
${1:-describe the data: summarize the file type, CRS, extent, and any notable properties.}
For vector files, if the question references a specific attribute, run an additional analysis:
python3 -c "
import geoai
result = geoai.analyze_vector_attributes('RESOLVED_PATH')
print(result)
"Step 5 -- Update state
Resolve the state directory:
STATE_DIR=""
test -f .geoai-skills/state.json && STATE_DIR=".geoai-skills"
PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")"
PROJECT_ID="$(echo "$PROJECT_ROOT" | tr '/' '-')"
test -f "$HOME/.geoai-skills/$PROJECT_ID/state.json" && STATE_DIR="$HOME/.geoai-skills/$PROJECT_ID"If STATE_DIR is set, update it with the inspected file info:
python3 -c "
import json, os
state_file = 'STATE_DIR/state.json'
state = {}
if os.path.exists(state_file):
with open(state_file) as f:
state = json.load(f)
state['last_inspected'] = {
'path': 'RESOLVED_PATH',
'type': 'TYPE',
}
with open(state_file, 'w') as f:
json.dump(state, f, indent=2)
"Replace STATE_DIR, RESOLVED_PATH, and TYPE (raster or vector) with actual values.
If no state directory exists yet, skip this step silently.
Step 6 -- Suggest next steps
After reporting, briefly mention:
- For raster files: "To process this raster (clip, mosaic, stack bands), use
/geoai-skills:process-raster. To run AI detection on it, use/geoai-skills:detect-objects." - For vector files: "To download more vector data for this area, use
/geoai-skills:overture-data."
Keep suggestions brief and show them only once.
Error handling
- If
python3is not found orimport geoaifails, delegate to/geoai-skills:install-geoai. - If rasterio or geopandas fails to read the file, try the GDAL/OGR fallback:
python3 -c "
import geoai
info = geoai.get_raster_info_gdal('RESOLVED_PATH')
for k, v in info.items():
print(f'{k}: {v}')
"Or for vectors:
python3 -c "
import geoai
info = geoai.get_vector_info_ogr('RESOLVED_PATH')
for k, v in info.items():
print(f'{k}: {v}')
"Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

