inspect-geo

Name: inspect-geo
Author: opengeos

23stars2forks

How to install inspect-geo?

opengeos/geoai-skills/inspect-geo

$npx -y skills add opengeos/geoai-skills --skill inspect-geo

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	You are helping the user inspect a geospatial data file.
2
3	Filename given: `$0`
4	Question: `${1:-describe the data}`
5
6	Follow these steps in order, stopping and reporting clearly if any step fails.
7
8	## Step 1 -- Resolve the file path
9
10	If `$0` looks like an absolute path, use it directly. Otherwise search for it:
11
12	```bash
13	find "$PWD" -name "$0" -not -path '/.git/' 2>/dev/null
14	```
15
16	- Zero results -> tell the user the file was not found and stop.
17	- More than one result -> list all matches, ask the user to re-run with a fuller path, and stop.
18	- Exactly one result -> use that full path as `RESOLVED_PATH`.
19
20	## Step 2 -- Classify the file type
21
22	Determine whether the file is raster or vector based on its extension:
23
24	- Raster: `.tif`, `.tiff`, `.img`, `.jp2`, `.vrt`, `.nc`, `.hdf`
25	- Vector: `.geojson`, `.json`, `.shp`, `.gpkg`, `.parquet`, `.geoparquet`, `.fgb`, `.kml`
26
27	If the extension is ambiguous, try raster first, then vector.
28
29	## Step 3 -- Run the appropriate inspection
30
31	### Raster files
32
33	```bash
34	python3 -c "
35	import geoai
36
37	info = geoai.get_raster_info('RESOLVED_PATH')
38	for k, v in info.items():
39	print(f'{k}: {v}')
40
41	print('---')
42	print('Band Statistics:')
43	stats = geoai.get_raster_stats('RESOLVED_PATH')
44	for k, v in stats.items():
45	print(f'{k}: {v}')
46	"
47	```
48
49	### Vector files
50
51	```bash
52	python3 -c "
53	import geoai
54
55	info = geoai.get_vector_info('RESOLVED_PATH')
56	for k, v in info.items():
57	print(f'{k}: {v}')
58	"
59	```
60
61	Replace `RESOLVED_PATH` with the actual absolute path before running.
62
63	## Step 4 -- Answer the user's question
64
65	Using the metadata retrieved in Step 3, answer:
66
67	`${1:-describe the data: summarize the file type, CRS, extent, and any notable properties.}`
68
69	For vector files, if the question references a specific attribute, run an additional analysis:
70
71	```bash
72	python3 -c "
73	import geoai
74	result = geoai.analyze_vector_attributes('RESOLVED_PATH')
75	print(result)
76	"
77	```
78
79	## Step 5 -- Update state
80
81	Resolve the state directory:
82
83	```bash
84	STATE_DIR=""
85	test -f .geoai-skills/state.json && STATE_DIR=".geoai-skills"
86	PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null \|\| echo "$PWD")"
87	PROJECT_ID="$(echo "$PROJECT_ROOT" \| tr '/' '-')"
88	test -f "$HOME/.geoai-skills/$PROJECT_ID/state.json" && STATE_DIR="$HOME/.geoai-skills/$PROJECT_ID"
89	```
90
91	If `STATE_DIR` is set, update it with the inspected file info:
92
93	```bash
94	python3 -c "
95	import json, os
96	state_file = 'STATE_DIR/state.json'
97	state = {}
98	if os.path.exists(state_file):
99	with open(state_file) as f:
100	state = json.load(f)
101	state['last_inspected'] = {
102	'path': 'RESOLVED_PATH',
103	'type': 'TYPE',
104	}
105	with open(state_file, 'w') as f:
106	json.dump(state, f, indent=2)
107	"
108	```
109
110	Replace `STATE_DIR`, `RESOLVED_PATH`, and `TYPE` (raster or vector) with actual values.
111
112	If no state directory exists yet, skip this step silently.
113
114	## Step 6 -- Suggest next steps
115
116	After reporting, briefly mention:
117
118	- 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`."
119	- For vector files: "To download more vector data for this area, use `/geoai-skills:overture-data`."
120
121	Keep suggestions brief and show them only once.
122
123	## Error handling
124
125	- If `python3` is not found or `import geoai` fails, delegate to `/geoai-skills:install-geoai`.
126	- If rasterio or geopandas fails to read the file, try the GDAL/OGR fallback:
127
128	```bash
129	python3 -c "
130	import geoai
131	info = geoai.get_raster_info_gdal('RESOLVED_PATH')
132	for k, v in info.items():
133	print(f'{k}: {v}')
134	"
135	```
136
137	Or for vectors:
138
139	```bash
140	python3 -c "
141	import geoai
142	info = geoai.get_vector_info_ogr('RESOLVED_PATH')
143	for k, v in info.items():
144	print(f'{k}: {v}')
145	"
146	```

People who liked this also viewed

6 picks

Type

azure-kustoQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clustersSkillsJul 2026470k1.3k
lark-base飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、workflow、角色权限；遇到 Base/多维表格/bitable 或 /base/ 链接时使用。文件导入转 lark-drive，认证/授权转 lark-shared。SkillsJul 2026382k16k
lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-vc）、待办任务（走 lark-task）。SkillsJul 2026380k16k
shadcnManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. AppliSkillsJul 2026246k120k
xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.SkillsJul 2026139k163k
firebase-data-connectAgent Skills for FirebaseSkillsJul 2026108k387

inspect-geo

23stars2forks

View on GitHub

How to install inspect-geo?

opengeos/geoai-skills/inspect-geo

$npx -y skills add opengeos/geoai-skills --skill inspect-geo

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	You are helping the user inspect a geospatial data file.
2
3	Filename given: `$0`
4	Question: `${1:-describe the data}`
5
6	Follow these steps in order, stopping and reporting clearly if any step fails.
7
8	## Step 1 -- Resolve the file path
9
10	If `$0` looks like an absolute path, use it directly. Otherwise search for it:
11
12	```bash
13	find "$PWD" -name "$0" -not -path '/.git/' 2>/dev/null
14	```
15
16	- Zero results -> tell the user the file was not found and stop.
17	- More than one result -> list all matches, ask the user to re-run with a fuller path, and stop.
18	- Exactly one result -> use that full path as `RESOLVED_PATH`.
19
20	## Step 2 -- Classify the file type
21
22	Determine whether the file is raster or vector based on its extension:
23
24	- Raster: `.tif`, `.tiff`, `.img`, `.jp2`, `.vrt`, `.nc`, `.hdf`
25	- Vector: `.geojson`, `.json`, `.shp`, `.gpkg`, `.parquet`, `.geoparquet`, `.fgb`, `.kml`
26
27	If the extension is ambiguous, try raster first, then vector.
28
29	## Step 3 -- Run the appropriate inspection
30
31	### Raster files
32
33	```bash
34	python3 -c "
35	import geoai
36
37	info = geoai.get_raster_info('RESOLVED_PATH')
38	for k, v in info.items():
39	print(f'{k}: {v}')
40
41	print('---')
42	print('Band Statistics:')
43	stats = geoai.get_raster_stats('RESOLVED_PATH')
44	for k, v in stats.items():
45	print(f'{k}: {v}')
46	"
47	```
48
49	### Vector files
50
51	```bash
52	python3 -c "
53	import geoai
54
55	info = geoai.get_vector_info('RESOLVED_PATH')
56	for k, v in info.items():
57	print(f'{k}: {v}')
58	"
59	```
60
61	Replace `RESOLVED_PATH` with the actual absolute path before running.
62
63	## Step 4 -- Answer the user's question
64
65	Using the metadata retrieved in Step 3, answer:
66
67	`${1:-describe the data: summarize the file type, CRS, extent, and any notable properties.}`
68
69	For vector files, if the question references a specific attribute, run an additional analysis:
70
71	```bash
72	python3 -c "
73	import geoai
74	result = geoai.analyze_vector_attributes('RESOLVED_PATH')
75	print(result)
76	"
77	```
78
79	## Step 5 -- Update state
80
81	Resolve the state directory:
82
83	```bash
84	STATE_DIR=""
85	test -f .geoai-skills/state.json && STATE_DIR=".geoai-skills"
86	PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null \|\| echo "$PWD")"
87	PROJECT_ID="$(echo "$PROJECT_ROOT" \| tr '/' '-')"
88	test -f "$HOME/.geoai-skills/$PROJECT_ID/state.json" && STATE_DIR="$HOME/.geoai-skills/$PROJECT_ID"
89	```
90
91	If `STATE_DIR` is set, update it with the inspected file info:
92
93	```bash
94	python3 -c "
95	import json, os
96	state_file = 'STATE_DIR/state.json'
97	state = {}
98	if os.path.exists(state_file):
99	with open(state_file) as f:
100	state = json.load(f)
101	state['last_inspected'] = {
102	'path': 'RESOLVED_PATH',
103	'type': 'TYPE',
104	}
105	with open(state_file, 'w') as f:
106	json.dump(state, f, indent=2)
107	"
108	```
109
110	Replace `STATE_DIR`, `RESOLVED_PATH`, and `TYPE` (raster or vector) with actual values.
111
112	If no state directory exists yet, skip this step silently.
113
114	## Step 6 -- Suggest next steps
115
116	After reporting, briefly mention:
117
118	- 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`."
119	- For vector files: "To download more vector data for this area, use `/geoai-skills:overture-data`."
120
121	Keep suggestions brief and show them only once.
122
123	## Error handling
124
125	- If `python3` is not found or `import geoai` fails, delegate to `/geoai-skills:install-geoai`.
126	- If rasterio or geopandas fails to read the file, try the GDAL/OGR fallback:
127
128	```bash
129	python3 -c "
130	import geoai
131	info = geoai.get_raster_info_gdal('RESOLVED_PATH')
132	for k, v in info.items():
133	print(f'{k}: {v}')
134	"
135	```
136
137	Or for vectors:
138
139	```bash
140	python3 -c "
141	import geoai
142	info = geoai.get_vector_info_ogr('RESOLVED_PATH')
143	for k, v in info.items():
144	print(f'{k}: {v}')
145	"
146	```

People who liked this also viewed

6 picks

Type