Back to Prompt Library
implementation
Build the application
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Wildfire Exposure Boundary Metadata Auditor
Format
Code-aware
Lines
61
Sections
11
Linked challenge
Build a Wildfire Exposure Boundary Metadata Auditor
Prompt source
Original prompt text with formatting preserved for inspection.
61 lines
11 sections
No variables
1 code block
## Build
Evaluate commercial real estate exposure locations by compiling intersecting STAC metadata records. Identify available high-resolution multispectral imagery links for defensive vegetation buffer audits using an LLM-assisted metadata retrieval workflow.
## User
Commercial Property Risk Surveyor
## Workflow
1. Load commercial facility polygon geometries and perimeter buffer specifications.
2. Discover recent high-resolution STAC Items covering the extended perimeter zones.
3. Extract valid spatial asset links representing optical imagery bands from the STAC records.
4. Generate a structured metadata retrieval report for downstream vegetation analysis by human reviewers.
## Interface
Web inspection terminal presenting property boundary overlays and retrieved STAC metadata links.
## Data
Query open STAC Catalog collections for Sentinel-2 or NAIP metadata, or utilize bundled local STAC GeoJSON files.
Starter examples below are synthetic. They are not downloaded records.
## Source
[STAC specification](https://raw.githubusercontent.com/radiantearth/stac-spec/master/README.md)
Traverses STAC Collections and Item metadata to parse asset bounding boxes and multispectral imagery links.
## Tools
anthropic-claude, pystac, shapely.
Claude parses complex STAC JSON schemas to extract valid optical imagery links and formats structured retrieval summaries.
Hosted Claude API for contextual JSON parsing and metadata audit reporting.
## Deliverables
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.
## Acceptance
- Queries STAC catalogs to find items intersecting property polygons.
- Successfully filters items containing optical imagery asset links.
- Emits human-readable metadata retrieval summaries for property inspection teams.
## Starter Examples
```json
[
{
"input": {
"facility_id": "FAC-WUI-01",
"buffer_clearance_m": 12.5,
"stac_collection": "naip"
},
"expected_output": {
"facility_id": "FAC-WUI-01",
"imagery_links_found": 2,
"metadata_status": "READY_FOR_REVIEW",
"record_type": "simplified synthetic app record"
}
},
{
"input": {
"facility_id": "FAC-WUI-02",
"buffer_clearance_m": 45,
"stac_collection": "naip"
},
"expected_output": {
"facility_id": "FAC-WUI-02",
"imagery_links_found": 0,
"metadata_status": "NO_IMAGERY_FOUND",
"record_type": "simplified synthetic app record"
}
}
]
```
## Safety
Provides preliminary metadata screening; does not execute physical site audits or replace qualified municipal fire marshals.
Use mock external writes. Require human review before any real deployment.Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.