# Overture Data

> >

- **Type:** Skill
- **Install:** `agentstack add skill-opengeos-geoai-skills-overture-data`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [opengeos](https://agentstack.voostack.com/s/opengeos)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [opengeos](https://github.com/opengeos)
- **Source:** https://github.com/opengeos/geoai-skills/tree/main/skills/overture-data

## Install

```sh
agentstack add skill-opengeos-geoai-skills-overture-data
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

You are helping the user download Overture Maps data using geoai.

Input: `$@`

Follow these steps in order.

## Step 1 -- Parse arguments

Extract:
- `$0` or the first positional argument as the Overture data type
- `--bbox minx,miny,maxx,maxy` as the bounding box (required)
- `--output FILE` as the output file path (optional, default: `./_overture.gpkg`)

Valid Overture data types:
`address`, `building`, `building_part`, `division`, `division_area`,
`division_boundary`, `place`, `segment`, `connector`, `infrastructure`,
`land`, `land_cover`, `land_use`, `water`

If the data type is not recognized, print the list of valid types and ask the user to pick one.

If the user provided natural language (e.g. "get buildings in downtown Nashville"), extract the data type and either infer or ask for the bounding box.

## Step 2 -- Validate the bounding box

Confirm the bounding box has 4 numeric values:
- `minx /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:

```bash
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.setdefault('downloaded_files', [])
state['downloaded_files'].append('OUTPUT_PATH')
with open(state_file, 'w') as f:
    json.dump(state, f, indent=2)
"
```

## Step 5 -- Report results

Summarize:
- Data type downloaded
- Number of features
- Output file path and size
- Column summary
- CRS and spatial extent

Then suggest: *"Use `/geoai-skills:inspect-geo` to examine the downloaded data in detail."*

## Error handling

- **`import geoai` fails** -> delegate to `/geoai-skills:install-geoai`.
- **`overturemaps` not installed** -> suggest `pip install "geoai-py[extra]"` which includes the overturemaps dependency.
- **No features found** -> suggest expanding the bounding box or trying a different data type.
- **Network error** -> report and suggest retrying.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [opengeos](https://github.com/opengeos)
- **Source:** [opengeos/geoai-skills](https://github.com/opengeos/geoai-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** yes
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-opengeos-geoai-skills-overture-data
- Seller: https://agentstack.voostack.com/s/opengeos
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.