geospatial-data-discovery
/geospatial-data-discovery
Wyszukuje i ocenia miarodajne zbiory i katalogi danych geoprzestrzennych pod kątem pokrycia, znaczenia cech, dostępu, licencji, kompletności i wersji, w tym katalogi STAC i Portolan.
- Autor
- jaakla ↗
- Repozytorium
- open-gis ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 7
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wyszukuje i ocenia miarodajne zbiory i katalogi danych geoprzestrzennych pod kątem pokrycia, znaczenia cech, dostępu, licencji, kompletności i wersji, w tym katalogi STAC i Portolan.
Oryginalny opis (EN)
Find and assess authoritative geospatial datasets or catalogs against known requirements: coverage, feature meaning, access, license, completeness, versions and reproducible pinning. Use for public sources, STAC/Portolan catalogs and read-only discovery of user data. Route joint source/compute/storage/delivery architecture to open-map-stack; do not turn a bounded lookup into a full analysis project.
Jak działa
- Discover and assess
- Boundaries and resources
Podgląd SKILL.md
--- name: geospatial-data-discovery description: "Find and assess authoritative geospatial datasets or catalogs against known requirements: coverage, feature meaning, access, license, completeness, versions and reproducible pinning. Use for public sources, STAC/Portolan catalogs and read-only discovery of user data. Route joint source/compute/storage/delivery architecture to open-map-stack; do not turn a bounded lookup into a full analysis project." metadata: version: "0.4.0" --- # Geospatial data discovery Find data that answers the user's question, and show what is known about its fitness. Dataset names, convenient APIs and plausible-looking geometries are not evidence that the features have the intended meaning. ## Discover and assess 1. Establish the area, time/version, feature semantics, necessary attributes, resolution, completeness and intended use. Ask only for consequential missing requirements; record assumptions that are safe to proceed with. 2. Read `references/data-sources.md` for public sources and STAC/Portolan catalogs. For the user's warehouse/database, read `references/user-data-sources.md`; use credentials by reference and read-only inspection. Snapshot materialization follows the existing authorization boundary. Before presenting current availability, coverage or licensing as verified, open the provider's actual metadata/download/license pages during this task. Reference notes are discovery leads, not evidence of a fresh lookup. Cite the pages checked and the check date; if access is unavailable, label the recommendation unverified and state what is missing. 3. Prefer the authoritative provider for the requested meaning. Verify fields and code lists against current provider metadata (report unavailable access): ownership, active status, eligibility and missing values must not be inferred from a generic category. Preserve unknowns as unknown. Official status alone does not prove that every alternative derives from that source or is less current; support comparative claims with evidence. 4. Check coverage and completeness using provider counts, pagination, catalog structure, partitions and spatial/temporal filters as applicable. Distinguish a sample from a complete extract and a partial catalog from absent data. 5. Identify a reproducible version or immutable snapshot, access method, retrieval time and license/attribution requirements. A URL containing `latest`, a filename or a retrieval date alone is not an immutable pin; retain snapshot bytes and their content hash when the source is mutable. Report unresolved license or retention constraints without inventing terms or promising a future rerun. Return a concise source assessment: provider/dataset, authoritative link, coverage/time, relevant fields and predicates, access/pin strategy, completeness evidence and material limitations. Compare alternatives when they change the answer; do not download an entire dataset just to establish its existence. When the user has dlt, Dagster, dbt, QGIS or Observable in their stack, read `references/established-stack.md` for ownership and integration boundaries. Preserve their chosen tools; retain source pins, GIS correctness and reproducible evidence. Do not duplicate their SQL, ingestion or scheduler definitions. ## Boundaries and resources Use `references/formats-and-crs.md` when inspecting coordinate systems, formats or spatial extents. A bounded discovery answer does not require `project.yaml`, a canonical pipeline or presentation artifacts. If the user asks for the actual multi-stage analysis, use an installed `open-map-stack` or `reproducible-gis-project`, or explain the needed next step; do not label a source assessment as a completed material analysis. When source choice depends on unresolved compute placement, continental scale, team concurrency or delivery architecture, keep those coupled decisions with the generalist. Do not choose an engine merely because a dataset is easy to query with it. No project template, worked example or OpenMapStack CLI is needed for a source assessment. If the task expands into a project, hand off the source assessment to an installed `open-map-stack` or `reproducible-gis-project`. No sibling skill or third-party installation is required for bounded discovery. For optional product expertise, read `references/companion-skills.md`. Keep GIS correctness and the task boundaries above when using a companion.
Pliki w paczce (7)
- SKILL.md 4 KB
- agents/openai.yaml 1 KB
- references/companion-skills.md 3 KB
- references/data-sources.md 23 KB
- references/established-stack.md 9 KB
- references/formats-and-crs.md 21 KB
- references/user-data-sources.md 11 KB
Wersje
W bazie nie ma innych skilli o nazwie geospatial-data-discovery.
Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 13.11.2026 · wersja paczki 4a998a3a6ac9 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 95reading-portolan
Przegląda i analizuje dane z katalogu Portolan (STAC, GeoParquet), łączy zbiory w DuckDB i tworzy mapy interaktywne. - 100portolan-cli
Obsługuje Portolan CLI do publikowania, zarządzania i konwersji katalogów danych geoprzestrzennych w formatach cloud-native: init, add, check, push, pull, sync i partycjonowanie. - 100portolan-cli
Obsługuje Portolan CLI do publikowania, zarządzania i konwersji katalogów danych geoprzestrzennych w formatach cloud-native: init, add, check, push, pull, sync i partycjonowanie. - 100reading-portolan
Pomaga badać, odpytywać i wizualizować dane z katalogu Portolan opartego na STAC, na przykład przez zapytania DuckDB do GeoParquet i mapy MapLibre. - 100open-map-stack
Planuje i prowadzi wieloetapowe prace GIS, dobierając autorytatywne źródła, moc obliczeniową, przechowywanie i dostarczanie: analizy wektorowe, rastrowe, chmury punktów, routing, QGIS i kafelki map. - 90geospatial
Analizuje wzorce przestrzenne danych: odległości, skupiska geograficzne i dostępność, gdy dane mają współrzędne.