Using Geoscience Skills
Meta-skill for discovering, routing, and composing the geoscience skills library.
This skill maps user intent to domain skills, workflow skills, slash commands, and agents.
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 |
| 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 |
| inversion, DC resistivity, magnetics, gravity, EM |
simpeg |
Inversion |
| 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 |
| 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 |
| 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 |
| 3D visualization, mesh, VTK, point cloud |
pyvista |
Visualization |
| data download, sample data, cache, fetch |
pooch |
Utilities |
Workflow Skills
Workflow skills chain multiple domain skills into end-to-end pipelines.
| Workflow |
Slash Command |
Skill Chain |
| Seismic Interpretation |
/seismic-workflow |
segyio -> obspy -> bruges -> disba -> pyvista |
| Well Log Evaluation |
/well-analysis |
lasio/dlisio -> welly -> petropy -> striplog -> pyvista |
| Geological Modelling |
/model-3d |
gemgis -> gempy/loopstructural -> pyvista |
| Geophysical Inversion |
/inversion-workflow |
simpeg/pygimli -> verde -> pyvista |
| Rock Physics & AVO |
/rock-physics |
lasio/welly -> bruges -> segyio |
Available Agents
| Agent |
Purpose |
Typical Trigger |
data-qc-reviewer |
Automated data quality checks across formats |
"QC my data", "check data quality" |
geoscience-mentor |
Guided explanations of geoscience concepts and methods |
"explain", "teach me", "what is" |
All 30 Domain Skills by Category
Seismic and Seismology
segyio -- SEG-Y file I/O, trace and header access
obspy -- seismological waveform processing, FDSN services
disba -- surface wave dispersion (Rayleigh, Love)
Well Log Analysis
lasio -- LAS file reading and writing
dlisio -- DLIS/RP66 binary well log parsing
welly -- well data analysis, curve QC, multi-well projects
petropy -- petrophysical analysis, formation evaluation
striplog -- lithological and stratigraphic log display
3D Geological Modelling
gempy -- implicit 3D geological modelling
loopstructural -- 3D modelling with fold and fault support
gemgis -- spatial data preprocessing for GemPy
Geophysical Inversion
simpeg -- multi-method geophysical inversion framework
pygimli -- ERT, SRT, IP inversion with simple API
devito -- symbolic PDE solver for wave propagation
pylops -- linear operators for inverse problems
Potential Fields and Rock Physics
harmonica -- gravity and magnetic data processing
bruges -- AVO, Gassmann, wavelets, elastic moduli
Spatial Analysis and Geostatistics
verde -- spatial gridding and interpolation
geostatspy -- variograms, kriging (GSLIB-style)
scikit-gstat -- geostatistics with scikit-learn API
gnnwr -- geographically weighted neural network regression
Hydrology and Surface Processes
pastas -- groundwater time series modelling
landlab -- landscape evolution modelling
Structural Geology and Geochemistry
mplstereonet -- stereonet plots for orientation data
pyrolite -- geochemical analysis and diagrams
Near-Surface Geophysics
gprpy -- GPR data processing
mtpy -- magnetotelluric data analysis
Data Formats and Visualization
xarray -- NetCDF, multi-dimensional labeled arrays
pyvista -- 3D mesh visualization and analysis
pooch -- data file fetching and caching
Skill Composition Rules
Chain skills when a task spans multiple stages of a geoscience workflow.
Composition Patterns
Data Loading -> Processing -> Modelling -> Visualization
1. Always start with a data I/O skill (segyio, lasio, dlisio, xarray)
2. Use processing skills for QC and transformation (welly, obspy, verde)
3. Apply domain modelling (bruges, gempy, simpeg, pygimli)
4. Finish with visualization (pyvista, matplotlib via domain skill)
When to Chain vs Use Standalone
| Scenario |
Approach |
| Single file format question |
Standalone domain skill |
| End-to-end analysis pipeline |
Workflow skill to orchestrate |
| Data QC across formats |
data-qc-reviewer agent |
| Concept explanation |
geoscience-mentor agent |
| Multi-library code generation |
Chain domain skills in order |
Dependency Awareness
When composing skills, respect data flow:
# Correct: segyio loads, obspy processes, bruges models
import segyio
import obspy
from bruges.reflection import zoeppritz
# Load with segyio
with segyio.open('seismic.sgy') as f:
data = f.trace[:]
# Process with obspy (convert to Stream if needed)
# Model with bruges
Rpp = zoeppritz(vp1, vs1, rho1, vp2, vs2, rho2, theta)
When to Use This Skill
This is the discovery and routing skill. Use it when:
- Starting a new geoscience coding session and unsure which library to use
- A user request spans multiple geoscience domains
- You need to find the right slash command or workflow for a task
- Composing multiple domain skills into a pipeline
- Looking up which skill handles a specific file format or analysis type
This skill does not perform any analysis itself. It directs to the appropriate
domain skill, workflow skill, or agent for execution.
Quick Decision Tree
User wants to...
|
+-- Load/write a file? --> Check format:
| SEG-Y -> segyio LAS -> lasio DLIS -> dlisio
| NetCDF -> xarray VTK -> pyvista
|
+-- Process signals? --> obspy (seismology), welly (well logs)
|
+-- Build a model?
| 3D geology -> gempy or loopstructural
| Rock physics -> bruges
| Inversion -> simpeg or pygimli
|
+-- Visualize results? --> pyvista (3D), matplotlib (2D via domain skill)
|
+-- Run a full pipeline? --> Use workflow skills above
1---2name: using-geoscience-skills3skill_type: meta4description: |5 Foundation skill for the geoscience skills library. Routes user intent6 to the correct domain skills, slash commands, and workflow skills.7 Loaded automatically at session start via SessionStart hook.8version: 1.0.09author: Geoscience Skills10license: MIT11tags: [Geoscience, Skills, Routing, Discovery, Workflows, Agents]12dependencies: []13metadata:14 source: https://skillmd.com/skills/steadfastasart/using-geoscience-skills15---1617# Using Geoscience Skills1819Meta-skill for discovering, routing, and composing the geoscience skills library.20This skill maps user intent to domain skills, workflow skills, slash commands, and agents.2122## Domain Routing Table2324Match user intent keywords to the appropriate domain skill.2526| Keywords / Triggers | Skill | Domain |27|---------------------|-------|--------|28| SEG-Y, seismic traces, trace headers, inline, crossline | `segyio` | Seismic I/O |29| waveform, earthquake, FDSN, seismogram, miniSEED | `obspy` | Seismology |30| surface wave, dispersion, Rayleigh, Love wave | `disba` | Seismology |31| LAS, well logs, wireline, borehole curves | `lasio` | Well Logs |32| DLIS, RP66, array logs, modern well data | `dlisio` | Well Logs |33| well analysis, curve QC, multi-well, despike | `welly` | Well Logs |34| petrophysics, Sw, porosity, formation evaluation | `petropy` | Petrophysics |35| lithology, stratigraphy, striplog, facies log | `striplog` | Stratigraphy |36| 3D model, geology, implicit surface, faults | `gempy` | 3D Modelling |37| fold modelling, structural frame, Loop3D | `loopstructural` | 3D Modelling |38| GIS, spatial data prep, borehole to GemPy | `gemgis` | GIS Preprocessing |39| inversion, DC resistivity, magnetics, gravity, EM | `simpeg` | Inversion |40| ERT, SRT, IP, near-surface inversion | `pygimli` | Inversion |41| PDE, wave equation, finite differences, stencil | `devito` | Simulation |42| linear operator, inverse problem, sparsity | `pylops` | Inverse Problems |43| gravity, magnetic, Bouguer, upward continuation | `harmonica` | Potential Fields |44| AVO, Zoeppritz, Gassmann, fluid substitution, wavelet | `bruges` | Rock Physics |45| gridding, interpolation, spatial, Verde | `verde` | Spatial Analysis |46| variogram, kriging, GSLIB, geostatistics | `geostatspy` | Geostatistics |47| variogram fitting, scikit-learn style geostat | `scikit-gstat` | Geostatistics |48| spatial regression, GWR, GNNWR, non-stationarity, coefficient mapping | `gnnwr` | Spatial Regression |49| groundwater, time series, pumping test | `pastas` | Hydrology |50| landscape, erosion, surface processes, DEM | `landlab` | Surface Processes |51| stereonet, strike, dip, poles, structural | `mplstereonet` | Structural Geology |52| geochemistry, REE, spider diagram, ternary | `pyrolite` | Geochemistry |53| GPR, ground-penetrating radar, radargram | `gprpy` | Near-Surface |54| magnetotellurics, MT, impedance tensor | `mtpy` | Near-Surface |55| NetCDF, xarray, multi-dimensional, climate | `xarray` | Data Formats |56| 3D visualization, mesh, VTK, point cloud | `pyvista` | Visualization |57| data download, sample data, cache, fetch | `pooch` | Utilities |5859## Workflow Skills6061Workflow skills chain multiple domain skills into end-to-end pipelines.6263| Workflow | Slash Command | Skill Chain |64|----------|---------------|-------------|65| Seismic Interpretation | `/seismic-workflow` | segyio -> obspy -> bruges -> disba -> pyvista |66| Well Log Evaluation | `/well-analysis` | lasio/dlisio -> welly -> petropy -> striplog -> pyvista |67| Geological Modelling | `/model-3d` | gemgis -> gempy/loopstructural -> pyvista |68| Geophysical Inversion | `/inversion-workflow` | simpeg/pygimli -> verde -> pyvista |69| Rock Physics & AVO | `/rock-physics` | lasio/welly -> bruges -> segyio |7071## Available Agents7273| Agent | Purpose | Typical Trigger |74|-------|---------|-----------------|75| `data-qc-reviewer` | Automated data quality checks across formats | "QC my data", "check data quality" |76| `geoscience-mentor` | Guided explanations of geoscience concepts and methods | "explain", "teach me", "what is" |7778## All 30 Domain Skills by Category7980### Seismic and Seismology81- `segyio` -- SEG-Y file I/O, trace and header access82- `obspy` -- seismological waveform processing, FDSN services83- `disba` -- surface wave dispersion (Rayleigh, Love)8485### Well Log Analysis86- `lasio` -- LAS file reading and writing87- `dlisio` -- DLIS/RP66 binary well log parsing88- `welly` -- well data analysis, curve QC, multi-well projects89- `petropy` -- petrophysical analysis, formation evaluation90- `striplog` -- lithological and stratigraphic log display9192### 3D Geological Modelling93- `gempy` -- implicit 3D geological modelling94- `loopstructural` -- 3D modelling with fold and fault support95- `gemgis` -- spatial data preprocessing for GemPy9697### Geophysical Inversion98- `simpeg` -- multi-method geophysical inversion framework99- `pygimli` -- ERT, SRT, IP inversion with simple API100- `devito` -- symbolic PDE solver for wave propagation101- `pylops` -- linear operators for inverse problems102103### Potential Fields and Rock Physics104- `harmonica` -- gravity and magnetic data processing105- `bruges` -- AVO, Gassmann, wavelets, elastic moduli106107### Spatial Analysis and Geostatistics108- `verde` -- spatial gridding and interpolation109- `geostatspy` -- variograms, kriging (GSLIB-style)110- `scikit-gstat` -- geostatistics with scikit-learn API111- `gnnwr` -- geographically weighted neural network regression112113### Hydrology and Surface Processes114- `pastas` -- groundwater time series modelling115- `landlab` -- landscape evolution modelling116117### Structural Geology and Geochemistry118- `mplstereonet` -- stereonet plots for orientation data119- `pyrolite` -- geochemical analysis and diagrams120121### Near-Surface Geophysics122- `gprpy` -- GPR data processing123- `mtpy` -- magnetotelluric data analysis124125### Data Formats and Visualization126- `xarray` -- NetCDF, multi-dimensional labeled arrays127- `pyvista` -- 3D mesh visualization and analysis128- `pooch` -- data file fetching and caching129130## Skill Composition Rules131132Chain skills when a task spans multiple stages of a geoscience workflow.133134### Composition Patterns135136```text137Data Loading -> Processing -> Modelling -> Visualization1381391. Always start with a data I/O skill (segyio, lasio, dlisio, xarray)1402. Use processing skills for QC and transformation (welly, obspy, verde)1413. Apply domain modelling (bruges, gempy, simpeg, pygimli)1424. Finish with visualization (pyvista, matplotlib via domain skill)143```144145### When to Chain vs Use Standalone146147| Scenario | Approach |148|----------|----------|149| Single file format question | Standalone domain skill |150| End-to-end analysis pipeline | Workflow skill to orchestrate |151| Data QC across formats | `data-qc-reviewer` agent |152| Concept explanation | `geoscience-mentor` agent |153| Multi-library code generation | Chain domain skills in order |154155### Dependency Awareness156157When composing skills, respect data flow:158159```python160# Correct: segyio loads, obspy processes, bruges models161import segyio162import obspy163from bruges.reflection import zoeppritz164165# Load with segyio166with segyio.open('seismic.sgy') as f:167 data = f.trace[:]168169# Process with obspy (convert to Stream if needed)170# Model with bruges171Rpp = zoeppritz(vp1, vs1, rho1, vp2, vs2, rho2, theta)172```173174## When to Use This Skill175176This is the **discovery and routing** skill. Use it when:177178- Starting a new geoscience coding session and unsure which library to use179- A user request spans multiple geoscience domains180- You need to find the right slash command or workflow for a task181- Composing multiple domain skills into a pipeline182- Looking up which skill handles a specific file format or analysis type183184This skill does not perform any analysis itself. It directs to the appropriate185domain skill, workflow skill, or agent for execution.186187## Quick Decision Tree188189```text190User wants to...191 |192 +-- Load/write a file? --> Check format:193 | SEG-Y -> segyio LAS -> lasio DLIS -> dlisio194 | NetCDF -> xarray VTK -> pyvista195 |196 +-- Process signals? --> obspy (seismology), welly (well logs)197 |198 +-- Build a model?199 | 3D geology -> gempy or loopstructural200 | Rock physics -> bruges201 | Inversion -> simpeg or pygimli202 |203 +-- Visualize results? --> pyvista (3D), matplotlib (2D via domain skill)204 |205 +-- Run a full pipeline? --> Use workflow skills above206```