Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SteadfastAsArt/geoscience-skills --skill using-geoscience-skillsgit clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/steadfastasart/geoscience-skills/using-geoscience-skills)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/using-geoscience-skills"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/using-geoscience-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/using-geoscience-skills"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/using-geoscience-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01997 |
| Opus 5.5 | $0.00024 | $0.00799 |
| Sonnet 5.5 | $0.00012 | $0.00399 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
using-geoscience-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +13 lines bb6dd6c9eefa
- 1mo ago First seen · 125 lines · 61 tokens per session scan A 6d3e0e7b0ec5
using-geoscience-skills is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (70 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,997 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.
Other skills, from other repositories
obspy-seismology
Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.
xarray-netcdf
Labeled multi-dimensional array analysis with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, and CF conventions.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…