Using Geoscience Skills
Match the user's task to the available domain and workflow skills. Select only the steps needed for the requested result, and reuse data or code already supplied.
When to Use and Alternatives
Use this skill when the appropriate geoscience library is unclear, a request spans multiple domains, or several skills need to work together. For a named library or one focused operation, use its domain skill directly. For an established multi-step task, use the matching workflow skill below.
Routing Procedure
- Identify the requested deliverable, data format, existing inputs, and environment.
- Match a focused task with the domain table, or a multi-step task with the workflow table. Treat listed chains as available options, not mandatory stages.
- Check which skills are available in the current host. Read the selected skill's
SKILL.mdand only the reference files needed for the task, using the host's available file or resource access. - If a skill is missing or unavailable, continue with available documentation and capabilities where practical. State any material limitation; do not claim to have loaded or invoked a skill that was not accessible.
- Complete the user's requested deliverable with relevant validation. Ask for clarification only when missing information materially affects the result; continue independent work when possible.
Domain Routing Table
Match user intent keywords to the appropriate domain skill.
| Keywords / Triggers | Skill | Domain |
|---|---|---|
| SEG-Y, seismic traces, trace headers, inline, crossline | segyio | Seismic I/O |
| SEG-Y to xarray, labelled seismic cube, Dask seismic | segysak | Seismic I/O |
| waveform, earthquake, FDSN, seismogram, miniSEED | obspy | Seismology |
| surface wave, dispersion, Rayleigh, Love wave | disba | Seismology |
| LAS, well logs, wireline, borehole curves | lasio | Well Logs |
| DLIS, RP66, array logs, modern well data | dlisio | Well Logs |
| well analysis, curve QC, multi-well, despike | welly | Well Logs |
| petrophysics, Sw, porosity, formation evaluation | petropy | Petrophysics |
| lithology, stratigraphy, striplog, facies log | striplog | Stratigraphy |
| 3D model, geology, implicit surface, faults | gempy | 3D Modelling |
| fold modelling, structural frame, Loop3D | loopstructural | 3D Modelling |
| GIS, spatial data prep, borehole to GemPy | gemgis | GIS Preprocessing |
| existing licensed GeoLime project, mining block model API | geolime | Licensed Modelling |
| inversion, DC resistivity, magnetics, gravity, EM | simpeg | Inversion |
| TensorMesh, TreeMesh, cell/face operators, finite-volume mesh | discretize | Meshes |
| ERT, SRT, IP, near-surface inversion | pygimli | Inversion |
| PDE, wave equation, finite differences, stencil | devito | Simulation |
| linear operator, inverse problem, sparsity | pylops | Inverse Problems |
| gravity, magnetic, Bouguer, upward continuation | harmonica | Potential Fields |
| reference ellipsoid, normal gravity, geocentric latitude | boule | Geodesy |
| AVO, Zoeppritz, Gassmann, fluid substitution, wavelet | bruges | Rock Physics |
| gridding, interpolation, spatial, Verde | verde | Spatial Analysis |
| variogram, kriging, GSLIB, geostatistics | geostatspy | Geostatistics |
| variogram fitting, scikit-learn style geostat | scikit-gstat | Geostatistics |
| spatial regression, GWR, GNNWR, non-stationarity, coefficient mapping | gnnwr | Spatial Regression |
| groundwater, time series, pumping test | pastas | Hydrology |
| MODFLOW, aquifer flow, head, recharge, water budget | flopy | Hydrology |
| landscape, erosion, surface processes, DEM | landlab | Surface Processes |
| stereonet, strike, dip, poles, structural | mplstereonet | Structural Geology |
| geochemistry, REE, spider diagram, ternary | pyrolite | Geochemistry |
| GPR, ground-penetrating radar, radargram | gprpy | Near-Surface |
| magnetotellurics, MT, impedance tensor | mtpy | Near-Surface |
| NetCDF, xarray, multi-dimensional, climate | xarray | Data Formats |
| paleoclimate proxy, age ensemble, irregular spectrum | pyleoclim | Paleoclimate |
| 3D visualization, mesh, VTK, point cloud | pyvista | Visualization |
| GMT, PyGMT, map projection, geographic grid cartography | pygmt | Cartography |
| data download, sample data, cache, fetch | pooch | Utilities |
| Fatiando datasets, explicit dataset version, Ensaio | ensaio | Datasets |
| existing RockHound cache, legacy PREM loader migration | rockhound | Legacy Datasets |
Workflow Skills
Use the skill name directly when the host supports skill selection, or read the available workflow instructions. Natural-language requests can match these tasks.
| Skill Name | Typical Task | Relevant Domain Skills |
|---|---|---|
seismic-interpretation | Process or interpret seismic data; build a seismic-to-well tie | segyio, obspy, bruges, disba, pyvista |
well-log-evaluation | Evaluate formations from LAS or DLIS logs | lasio, dlisio, welly, petropy, striplog, pyvista |
geological-modelling | Build a 3D model from mapping, boreholes, or GIS inputs | gemgis, gempy or loopstructural, pyvista |
geophysical-inversion | Recover physical properties from ERT, EM, gravity, or magnetic data | simpeg or pygimli, verde, pyvista |
rock-physics-avo | Compute elastic properties, fluid substitution, AVO, or synthetics | lasio, welly, bruges, segyio |
hydrogeological-analysis | Combine well logs, groundwater head time series and aquifer hypotheses | lasio, welly, pastas, optionally flopy |
near-surface-geophysics | Compare GPR, ERT and MT evidence with matched coordinates and resolution | gprpy, pygimli or simpeg, mtpy |
climate-analysis | Analyse climate time series and grid spatial observations without leakage | xarray, verde, optionally pyleoclim |
Composition and Data Handoffs
- Start from the inputs already available. Data loading, modelling, plotting, and export are needed only when they contribute to the requested task.
- Carry units, coordinates, depth or time basis, array shapes, missing-value masks, and provenance across library boundaries. Ensure later stages use the intended processed output.
- Check each selected skill's
metadata.dependenciesagainst the environment. Dependency and complement lists are descriptive metadata, not package-installation commands or proof that another skill is available. - Choose compatible libraries and adapters for the selected branch. Do not assume alternatives produce interchangeable objects.
- Match validation to the deliverable: a corrected script, explanation, QC report, model, plot, or exported dataset may each complete the user's request.
Optional Role References
The repository's agents/data-qc-reviewer.md, agents/geoscience-mentor.md and
agents/cross-validation-reviewer.md are
optional role references for hosts that support them. Ordinary skill installation
may omit these files. Perform QC and explanations with available capabilities;
these roles and host-specific integrations are not requirements for routing or
executing the core skills.
Common Issues
| Issue | Response |
|---|---|
| A recommended skill is not installed | Use available guidance or capabilities and report any material gap. |
| A required Python package is unavailable | Inspect the project environment and dependency guidance before choosing a compatible setup or alternative. |
| Data is already loaded or processed | Begin at the relevant stage and verify the supplied data's assumptions. |
| Several libraries match the request | Choose by data format, required operation, existing environment, and requested result. |
