geoai-orchestrator
Route genuinely ambiguous or multi-stage geospatial work across specialist skills while enforcing shared CRS, validity, leakage, units, verification, and reproducibility rules. Use for requests spanning multiple stages such as acquisition, imagery, modeling, analysis, and map delivery, or for an explicit end-to-end pipeline. Never invoke for one domain merely because a parameter is unclear. Code implementation/review, backend or platform choice, and production-readiness review are direct specialist tasks. Do not add this skill as a layer around one specialist.
Muhammed Enes Duran · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add muend/geoai-skills --skill geoai-orchestratorAbout this skill
name: geoai-orchestrator description: >- Route genuinely ambiguous or multi-stage geospatial work across specialist skills while enforcing shared CRS, validity, leakage, units, verification, and reproducibility rules. Use for requests spanning multiple stages such as acquisition, imagery, modeling, analysis, and map delivery, or for an explicit end-to-end pipeline. Never invoke for one domain merely because a parameter is unclear. Code implementation/review, backend or platform choice, and production-readiness review are direct specialist tasks. Do not add this skill as a layer around one specialist. license: MIT metadata: author: Muhammed Enes Duran
GeoAI Orchestrator
The hub of an 18-skill geospatial module. Activate it for routing or pipeline composition, not as a mandatory wrapper around every spatial task. Its job: (1) diagnose what kind of spatial problem the user actually has, (2) design the pipeline across stages, (3) route each stage to the right specialist skill, and (4) enforce the module-wide invariants that every stage must obey.
Routing gate — read before producing any output
This orchestrator routes by invoking, never by naming. The gate below overrides every other section of this document, including the pipeline template.
- Invoke, do not list. Every specialist you select must be invoked with
the
Skilltool in the same response that selects it. Naming a skill in a table, plan, or prose sentence is not a handoff. A response that identifies the right specialist but does not invoke it has failed this skill's core function, no matter how accurate the diagnosis is. - Route every correction, not the first one. When a request contains multiple findings, defects, or stages, each one gets its own routing decision and its own invocation. Routing one item and handling the rest inline is a partial failure; the count of routed items must equal the count of items found.
- Never make routing conditional on permission. Do not write "say the word and I'll route", "I can hand this off if you want", "let me know and I'll bring in the specialist", or any equivalent. Offering to route later is the single most common failure of this skill. If you have identified the specialist, invoke it now.
- Clarification is not a substitute for routing. Missing detail about scope (which deliverable, which study area) does not block routing of the stages you have already identified. Ask the scope question and route in the same response. Only a request whose entire domain is undetermined may be routed-free, and then you must say which specialist becomes available under each candidate answer.
- Audit requests are
deliverrequests. "Audit this plan", "review this pipeline", "what is wrong with this workflow" require the completed audit, the routed corrections, and the revised plan in one response. Do not return findings and hold the corrections back for a follow-up turn.
If you cannot satisfy the gate, do not activate this skill — route the request directly to the single narrowest specialist instead.
Module map — route by problem type
| Stage / problem | Specialist skill |
|---|---|
| Data acquisition, formats, CRS, tiling, pipelines | geo-data-engineering |
| Satellite/aerial imagery, spectral indices, classification | remote-sensing-analysis |
| Planetary-scale archives, GEE Python API, cloud compositing | google-earth-engine |
| CNN/U-Net/ViT on EO data, segmentation, detection | geo-deep-learning |
| Autocorrelation, hotspots, clusters, spatial regression | spatial-statistics |
| Site selection, suitability, AHP/weighted overlay | mcda-suitability-analysis |
| Interpolation from point samples, kriging, variograms | geostatistics-interpolation |
| DEM, slope, watersheds, flow, viewshed | terrain-hydrology |
| LiDAR / point clouds, DTM/DSM/CHM, PDAL | point-cloud-lidar |
| Routing, service areas, accessibility, OD matrices | network-accessibility-analysis |
| GPS tracks, trajectories, stops/trips, map matching | movement-trajectory |
| Multi-temporal comparison, land cover change, trends | change-detection |
| Map design, choropleths, web maps, publication figures | cartography-geoviz |
| Spatial SQL, PostGIS, large-scale spatial joins | postgis-spatial-sql |
Local ArcGIS Pro, ArcPy, .aprx, or .gdb execution | arcgis-pro-automation |
This table selects specialists; it does not hand off to them. Every row you
select must be invoked under the routing gate. For cross-cutting method
standards (leakage, metrics, reproducibility), invoke ml-experiment-standards
and swe-devops-standards when their rules apply.
Pipeline design protocol
For any multi-stage request, produce a short pipeline plan BEFORE writing code, then invoke the specialists that plan names in the same response:
## Pipeline: <goal>
1. <stage> → <skill> → output: <artifact> → check: <verification criterion>
2. ...
Success criterion: <what the user can inspect to accept the result>
The plan is a routing manifest, not a proposal awaiting approval. Publishing the plan and stopping there is the failure mode this skill exists to prevent. Do not wait for confirmation before routing; confirmation is only ever sought for scope (which deliverable, which extent, which decision), and it is requested alongside the routed stages, never instead of them.
Every stage ends with a verification criterion. Spatial work fails silently (wrong CRS, empty joins, inverted axes produce plausible-looking garbage), so a stage without a check is not a stage.
Module-wide invariants (enforced in every stage)
- CRS is explicit, always. Report the CRS of every input on first
contact. Never compute area/distance/buffer in a geographic (degree)
CRS — reproject to an appropriate projected CRS (local UTM zone by
default via
gdf.estimate_utm_crs(); equal-area such as EPSG:69