Gemgis logo

Gemgis

Community
SteadfastAsArt
gemgis

Spatial data processing for geological modelling with GemPy. Use when the agent needs to: (1) Prepare spatial data for GemPy models, (2) Extract interface points from geological maps, (3) Process orientations/dip measurements, (4) Sample DEMs along profiles or cross-sections, (5) Convert between GIS formats and GemPy inputs, (6) Clip/transform vector/raster data for modeling, (7) Create model extents from geospatial bounds.

Overview

PublisherSteadfastAsArt
Repositorygeoscience-skills
Skill namegemgis
Stars
75
Forks
9
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SteadfastAsArt on GitHub. Read the source before you install it.

Installation

Install the Gemgis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SteadfastAsArt/geoscience-skills/tree/main/gemgis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skills.git /tmp/geoscience-skills
mkdir -p .claude/skills
cp -r /tmp/geoscience-skills/gemgis .claude/skills/gemgis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gemgis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gemgis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gemgis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GIS contacts and DEM elevations

Use GemGIS to extract geological observations from spatial data. Establish the horizontal CRS, vertical units/datum, geometry type and missing-data policy before sampling. Model coordinates must share a projected metre CRS; converting horizontal coordinates does not transform elevations or their datum.

Extract contact vertices

The following function accepts a single-band DEM already in a metre projected CRS, with elevations in metres. dem is an open Rasterio dataset, not a path. GemGIS repeats attributes when a line becomes multiple points: do not overwrite those attributes using the original feature index.

python
import gemgis as gg
from rasterio.transform import rowcol
import numpy as np
from pyproj import CRS

def contacts_at_dem(contacts, dem):
    crs = CRS.from_user_input(dem.crs)
    if (contacts.crs is None or not crs.is_projected or dem.count != 1
            or any(not np.isclose(a.unit_conversion_factor, 1.) for a in crs.axis_info[:2])):
        raise ValueError('Require a known vector CRS and a single-band metric DEM')
    if contacts.empty or not contacts.is_valid.all() or contacts.geometry.has_z.any():
        raise ValueError('Require valid nonempty 2D contact geometry')
    if 'formation' not in contacts or contacts['formation'].isna().any():
        raise ValueError('Formation labels are required')
    points = gg.vector.extract_xy(contacts.to_crs(dem.crs))
    xy = points[['X', 'Y']].to_numpy()
    rows, cols = np.asarray(rowcol(dem.transform, xy[:, 0], xy[:, 1]))
    if np.any((rows < 0) | (rows >= dem.height) | (cols < 0) | (cols >= dem.width)):
        raise ValueError('Vertices outside DEM')
    samples = np.ma.vstack(list(dem.sample(xy, indexes=1, masked=True)))[:, 0]
    if np.ma.getmaskarray(samples).any() or not np.isfinite(samples.data).all():
        raise ValueError('Missing DEM elevations')
    return gg.vector.extract_xyz(gdf=points, dem=dem)[['X', 'Y', 'Z', 'formation']]

Open with with rasterio.open(dem_path) as dem: and call this function while the dataset is open. Pixel sampling uses the containing cell; it is not bilinear interpolation. Do not fill NoData or outside-extent samples with zero.

Orientations and helper

Dip is in degrees, 0–90. Output azimuth is dip direction clockwise from DEM grid north, wrapped to [0, 360). Convert strike with (strike + 90) % 360 only when the source explicitly follows the right-hand rule. Preserve supplied polarity (+1/−1); the helper uses +1 only when the column is absent. Never clamp invalid dip. Declare --azimuth-reference dem-grid for bearings already relative to the DEM grid, or true-north for geographic bearings. The latter applies local meridian convergence only on locally conformal projections; other projections are rejected. Magnetic bearings need a documented declination correction first.

The preparation helper validates these rules, reprojects vectors to the DEM CRS, converts declared ft elevations to metres, and writes CSVs plus spatial_metadata.json into a fresh output directory. Its --target-crs is an assertion that must match the DEM; resample/reproject a raster separately when needed.

bash
python scripts/prepare_gempy_data.py --contacts contacts.gpkg \
  --orientations orientations.gpkg --azimuth-reference true-north --dem dem.tif --dem-z-unit m \
  --vertical-datum "documented source datum" --output-dir prepared

Resolve this command relative to the installed skill directory. The output schema uses X/Y/Z and formation, plus dip/azimuth/polarity for orientations; pass these to the current modelling library's input API rather than assuming all GemPy versions accept identical keyword arguments.

Conditional operations

Read profiles and extraction for sampled profiles and orientation conventions. Read CRS, clipping and raster handling for bounds order, masks, reprojection and provenance. Existing 3D geometry needs an explicit choice between measured Z and DEM Z before using this helper.

Verification scope

GemGIS 1.1.9, GeoPandas 1.1.4 and Rasterio 1.4.4 were checked with a real GeoTIFF/GeoPackage fixture: unequal vertex counts and nonconsecutive indices, CRS conversion, feet elevations, NoData, outside points, orientations and CLI CSV readback. Synthetic elevations test data handling, not field DEM accuracy or vertical-datum transformation.

Official GemGIS source, Rasterio sampling API, checked 2026-09-14.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gemgis AI skill do?

Spatial data processing for geological modelling with GemPy. Use when the agent needs to: (1) Prepare spatial data for GemPy models, (2) Extract interface points from geological maps, (3) Process orientations/dip measurements, (4) Sample DEMs along profiles or cross-sections, (5) Convert between GIS formats and GemPy inputs, (6) Clip/transform vector/raster data for modeling, (7) Create model extents from geospatial bounds.

Why use Gemgis on TypingMind?

Because you install it once and use it with any model. Gemgis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gemgis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SteadfastAsArt/geoscience-skills/tree/main/gemgis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gemgis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gemgis?

As many as you like. As long as a model supports skills, you can use Gemgis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gemgis AI skill free?

Yes. It is published on GitHub by SteadfastAsArt under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇