agentleFS
opengeosopengeos/geoai-skills/skills/install-geoai/SKILL.md

install-geoai

Skill31 starsChanged 8 months agoMITView on GitHub

Verify that the geoai Python package is installed and functional. If not, provide installation instructions. Optionally check extra dependencies for deep learning models.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If --check is present in $@, run a comprehensive dependency check:

    line 24
  2. Very specific:

    If --extras is present in $@, also check deep learning dependencies:

    line 42
  3. Distinctive:

    If geoai is not installed, tell the user:

    line 71
  4. Distinctive:

    Stop after showing the instructions.

    line 91

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Arguments: $@

Step 1 -- Check if geoai is importable

python3 -c "import geoai; print(f'geoai v{geoai.__version__}')"
  • Success -> report the version and continue to Step 2 if --check or --extras was passed, otherwise stop.
  • ImportError -> go to Step 3.

Step 2 -- Check optional dependencies

If --check is present in $@, run a comprehensive dependency check:

python3 -c "
deps = [
    'geoai', 'geopandas', 'rasterio', 'rioxarray', 'shapely',
    'leafmap', 'numpy', 'pandas', 'matplotlib',
]
for dep in deps:
    try:
        mod = __import__(dep)
        ver = getattr(mod, '__version__', 'unknown')
        print(f'{dep}: {ver}')
    except ImportError:
        print(f'{dep}: NOT INSTALLED')
"

If --extras is present in $@, also check deep learning dependencies:

python3 -c "
import sys
dl_deps = ['torch', 'torchvision', 'transformers', 'timm', 'segmentation_models_pytorch']
for dep in dl_deps:
    try:
        mod = __import__(dep)
        ver = getattr(mod, '__version__', 'unknown')
        print(f'{dep}: {ver}')
    except ImportError:
        print(f'{dep}: NOT INSTALLED')

try:
    import torch
    if torch.cuda.is_available():
        print(f'CUDA: {torch.version.cuda} (device: {torch.cuda.get_device_name(0)})')
    else:
        print('CUDA: not available (CPU only)')
except ImportError:
    print('CUDA: torch not installed')
"

Report the results and note any missing packages.

Step 3 -- Installation instructions

If geoai is not installed, tell the user:

geoai is not installed. Install it with:

pip install geoai-py

For GPU-accelerated AI models (object detection, segmentation), also install PyTorch:

pip install torch torchvision

For the full set of optional dependencies:

pip install "geoai-py[extra]"

Stop after showing the instructions. Do not attempt to install automatically unless the user explicitly asks.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.