Skills

A skill is a package of structured files that teaches an AI coding agent how to work with a specific tool or framework. The skill below was generated by Great Docs from this project’s documentation. Install it in your agent and it will be able to run commands, edit configuration, write content, and troubleshoot problems without step-by-step guidance from you.

Any agent — install with npx:

npx skills add https://lqgentner.github.io/freezebase/

Codex / OpenCode

Tell the agent:
Fetch the skill file at https://lqgentner.github.io/freezebase/skill.md and follow the instructions.

Manual — download the skill file:

curl -O https://lqgentner.github.io/freezebase/skill.md

Or browse the SKILL.md file.

SKILL.md

---
name: freezebase
description: >
  Lightweight geospatial helpers for reproducible MGRS grids and S3-backed raster workflows. Use when writing Python code that uses the freezebase package.
license: MIT
compatibility: Requires Python >=3.12.
---

# freezebase

Lightweight geospatial helpers for reproducible MGRS grids and S3-backed raster workflows.

## Installation

```bash
pip install freezebase
```

## API overview

### MGRS grid

10 km MGRS grid squares to align raster data onto one common grid.

- `mgrs.MGRSGrid`
- `mgrs.MGRSGeoBox`
- `mgrs.UTMZones`
- `mgrs.mgrs_to_crs`
- `mgrs.utm_to_crs`
- `mgrs.utms_to_epsgs`
- `mgrs.transform_shapely`

### Raster I/O

rasterio helpers that accept local paths and `s3://` URIs via UPath.

- `raster.rasterio_open`
- `raster.rewrite_tiff`
- `raster.write_cog`
- `raster.merge_tiffs`
- `raster.build_rasterio_profile`
- `raster.group_tiffs_by_crs`
- `raster.get_utm_zone_string`
- `raster.get_epsg_string`
- `raster.utm_zone_to_crs`
- `raster.COG_PROFILE`
- `raster.RASTERIO_PROFILE_DEFAULTS`

### VRT generation

Build VRT files without the Python GDAL dependency

- `vrt.create_decibel_vrt`
- `vrt.create_rgb_vrt`
- `vrt.build_vrt_mosaic`

### Downloads

HTTP downloads with UPath destinations

- `download.HTTPDownloader`
- `download.retry_request`

### S3

S3 `UPath` construction and retry configuration

- `s3.make_s3_upath`
- `s3.s3_env`

### Vector data

Cached vector datasets and GeoDataFrame helpers

- `vectordata.GeoVectorData`
- `vectordata.DatasetMetadata`
- `vectools.save_and_read_parquet`
- `vectools.drop_z_if_zero`
- `vectools.is_z_axis_zero`
- `vectools.simplify_multipolygons`

### Utilities

Shared helpers used across the package

- `set_loglevel`: Configure freezebase's logging levels
- `utils.get_cache_dir`
- `utils.get_data_dir`
- `utils.get_credentials_from_env`
- `utils.depends_on_optional`
- `utils.file_sha256`
- `utils.shorten_string`
- `utils.format_valid_options`
- `pandas_utils.clean_names`
- `progress.create_progress`
- `progress.track_progress`

## Resources

- [Full documentation](https://lqgentner.github.io/freezebase/)
- [llms.txt](llms.txt) — Indexed API reference for LLMs
- [llms-full.txt](llms-full.txt) — Comprehensive documentation for LLMs
- [Source code](https://github.com/lqgentner/freezebase)