Skip to content
Back to search

geoscience-skills

MarketplaceWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/steadfastasart--geoscience-skills/badge.svg)](/listings/steadfastasart--geoscience-skills)

HTML

<a href="/listings/steadfastasart--geoscience-skills"><img src="/api/listings/steadfastasart--geoscience-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Upstream skills CLI (recommended)

Run from the project where you want to use the skills. The installer supports multiple coding agents and manages their destination directories.

# Inspect all domain, workflow, and routing skills
npx skills add SteadfastAsArt/geoscience-skills --full-depth --list

# Select skills and target agents interactively
npx skills add SteadfastAsArt/geoscience-skills --full-depth

# Install a starting set for multiple agents
npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  --skill using-geoscience-skills lasio segyio --agent codex claude-code

# Install the whole collection for one agent
npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  --skill '*' --agent gemini-cli

# Install a workflow and the domain skills needed for it
npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  --skill well-log-evaluation lasio dlisio welly petropy striplog pyvista \
  --agent github-copilot

Keep `--full-depth` to include workflows nested under `workflows/`. Add `--global` for user scope; use `--copy` if you prefer copies to symlinks. Choosing a workflow does not automatically install its complementary skills or Python dependencies. Other targets include `windsurf`, `opencode`, `cline`, `roo`, and `openclaw`; consult the [upstream supported-agent list](https://github.com/vercel-labs/skills#supported-agents).

npx skills list
# Explicitly update installed skills when desired
npx skills update

From a local checkout

git clone https://github.com/SteadfastAsArt/geoscience-skills.git
# Run this in your target project; replace the path with your checkout location.
npx skills add /path/to/geoscience-skills --full-depth --agent codex

For manual installation, copy each selected **skill directory** to a directory supported by your agent. Preserve its `SKILL.md`, `references/`, and `scripts/`. For a workflow, copy `workflows/<name>/` as `<name>/` alongside the domain skills. Do not copy the whole repository into an agent's skill directory. Platform configuration and optional role guides are separate from skill installation. See [platform notes and the manual reading fallback](docs/COMPATIBILITY.md).

Python dependencies

Install the packages needed for your task in its Python environment. For example:

# LAS inspection and conversion
python -m pip install lasio pandas

# SEG-Y inspection and subsetting
python -m pip install segyio numpy

Skill `metadata.dependencies` records library requirements; installing a skill does not install or validate those packages. See [SKILLS.md](SKILLS.md) for additional domain-specific package lists.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 492 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "geoscience-skills",
  3. "owner": {
  4. "name": "Geoscience Skills"
  5. },
  6. "metadata": {
  7. "description": "48 geoscience skills for AI coding assistants covering seismic, well logs, geological modelling, geophysical inversion, geostatistics, spatial regression, and related workflows.",
  8. "version": "2.5.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "boule",
  13. "source": "./",
  14. "strict": false,
  15. "skills": [
  16. "./boule"
  17. ],
  18. "description": "Calculate reference-ellipsoid geometry, normal gravity and geodetic/geocentric coordinate conversions with Boule. Use for gravity reference corrections and planetary ellipsoids; this does not transform between geodetic datums or compute terrain corrections.",
  19. "version": "1.0.0"
  20. },
  21. {
  22. "name": "bruges",
  23. "source": "./",
  24. "strict": false,
  25. "skills": [
  26. "./bruges"
  27. ],
  28. "description": "Geophysical equations and rock physics calculations for seismic analysis. Use when the agent needs to: (1) Calculate AVO responses (Zoeppritz, Shuey, Aki-Richards), (2) Perform Gassmann fluid substitution, (3) Generate seismic wavelets (Ricker, Ormsby), (4) Compute reflectivity and synthetic seismograms, (5) Calculate elastic moduli from velocities, (6) Apply Gardner/Castagna empirical relations, (7) Model rock physics effects.",
  29. "version": "1.0.2"
  30. },
  31. {
  32. "name": "climate-analysis",
  33. "source": "./",
  34. "strict": false,
  35. "skills": [
  36. "./workflows/climate-analysis"
  37. ],
  38. "description": "Analyse labelled climate time series and gridded or station observations with checked calendars, aggregation, climatological baselines and spatial validation. Use for climate anomalies, regional summaries or station-to-grid analysis; distinguish descriptive analysis from future-time prediction.",
  39. "version": "1.0.1"
  40. },
  41. {
  42. "name": "devito",
  43. "source": "./",
  44. "strict": false,
  45. "skills": [
  46. "./devito"
  47. ],
  48. "description": "Symbolic PDE solver with automatic code generation for finite-difference computations. Use when the agent needs to: (1) Perform seismic wave propagation modeling, (2) Implement acoustic or elastic wave equations, (3) Run forward modeling for shot gathers, (4) Set up Full Waveform Inversion (FWI) workflows, (5) Implement Reverse Time Migration (RTM), (6) Create absorbing boundary conditions, (7) Generate optimized stencil code for CPUs/GPUs, (8) Solve custom PDEs with finite differences.",
  49. "version": "1.0.1"
  50. },
  51. {
  52. "name": "disba",
  53. "source": "./",
  54. "strict": false,
  55. "skills": [
  56. "./disba"
  57. ],
  58. "description": "Compute Rayleigh and Love wave phase/group dispersion and sensitivity kernels for one-dimensional isotropic layered Earth models. Use when forward modelling velocity profiles, comparing layered models, or preparing numerical derivatives for a separately defined inversion. Does not extract observed dispersion from waveforms or perform tomography.",
  59. "version": "1.0.2"
  60. },
  61. {
  62. "name": "discretize",
  63. "source": "./",
  64. "strict": false,
  65. "skills": [
  66. "./discretize"
  67. ],
  68. "description": "Create finite-volume meshes and discrete differential operators with discretize. Use for TensorMesh or TreeMesh geometry, cell/face/edge ordering, divergence, interpolation and meshes supporting SimPEG; use a physics solver for inversion itself.",
  69. "version": "1.0.0"
  70. },
  71. {
  72. "name": "dlisio",
  73. "source": "./",
  74. "strict": false,
  75. "skills": [
  76. "./dlisio"
  77. ],
  78. "description": "Read and parse DLIS (Digital Log Interchange Standard) and LIS (Log Information Standard) well log files. Use when the agent needs to: (1) Read/parse DLIS or LIS files, (2) Extract well log curves as numpy arrays, (3) Access file metadata and origin information, (4) Handle multi-frame or multi-file DLIS, (5) Convert DLIS to LAS or DataFrame, (6) Work with RP66 format well logs, (7) Process array or image log data.",
  79. "version": "1.0.2"
  80. },
  81. {
  82. "name": "ensaio",
  83. "source": "./",
  84. "strict": false,
  85. "skills": [
  86. "./ensaio"
  87. ],
  88. "description": "Fetch versioned Fatiando geoscience datasets with Ensaio and preserve their hashes, citations and data conventions. Use for reproducible sample-data acquisition and replacing supported RockHound datasets; the fetchers return paths for format-specific readers.",
  89. "version": "1.0.0"
  90. },
  91. {
  92. "name": "flopy",
  93. "source": "./",
  94. "strict": false,
  95. "skills": [
  96. "./flopy"
  97. ],
  98. "description": "Build, run, inspect and diagnose MODFLOW groundwater flow models with FloPy. Use for aquifer discretization, recharge and boundary conditions, hydraulic heads, groundwater budgets and MODFLOW 6 output; use Pastas for statistical head time series.",
  99. "version": "1.0.0"
  100. },
  101. {
  102. "name": "gemgis",
  103. "source": "./",
  104. "strict": false,
  105. "skills": [
  106. "./gemgis"
  107. ],
  108. "description": "Spatial data processing for geological modelling with GemPy. Use when the agent needs to: (1) Prepare spatial data for GemPy models, (2) Extract interface points from geological maps, (3) Process orientations/dip measurements, (4) Sample DEMs along profiles or cross-sections, (5) Convert between GIS formats and GemPy inputs, (6) Clip/transform vector/raster data for modeling, (7) Create model extents from geospatial bounds.",
  109. "version": "1.0.2"
  110. },
  111. {
  112. "name": "gempy",
  113. "source": "./",
  114. "strict": false,
  115. "skills": [
  116. "./gempy"
  117. ],
  118. "description": "3D structural geological modeling using implicit methods. Create geological models with faults, folds, and unconformities from surface points and orientations. Use when the agent needs to: (1) Build 3D geological models from surface contacts and orientations, (2) Model faults, unconformities, or intrusions, (3) Compute and visualize subsurface geology, (4) Export models to VTK or numpy arrays, (5) Generate gravity forward models, (6) Create cross-sections or 3D visualizations.",
  119. "version": "1.0.1"
  120. },
  121. {
  122. "name": "geolime",
  123. "source": "./",
  124. "strict": false,
  125. "skills": [
  126. "./geolime"
  127. ],
  128. "description": "Assess and maintain licensed GeoLime geological or mining-model workflows, checking the installed vendor API, drillhole conventions and model validation. Use when a project explicitly uses GeoLime; the public PyPI placeholder does not provide a working modelling API.",
  129. "version": "1.0.0"
  130. },
  131. {
  132. "name": "geological-modelling",
  133. "source": "./",
  134. "strict": false,
  135. "skills": [
  136. "./workflows/geological-modelling"
  137. ],
  138. "description": "3D geological modelling workflow from spatial data preparation through implicit surface modelling and 3D visualization. Use when building geological models from surface data, boreholes, or GIS inputs.",
  139. "version": "1.0.2"
  140. },
  141. {
  142. "name": "geophysical-inversion",
  143. "source": "./",
  144. "strict": false,
  145. "skills": [
  146. "./workflows/geophysical-inversion"
  147. ],
  148. "description": "Geophysical data inversion workflow from data loading through mesh creation, forward modelling, inversion, and result visualization. Use when inverting ERT, magnetics, gravity, or EM survey data.",
  149. "version": "1.0.2"
  150. },
  151. {
  152. "name": "geostatspy",
  153. "source": "./",
  154. "strict": false,
  155. "skills": [
  156. "./geostatspy"
  157. ],
  158. "description": "GSLIB-inspired geostatistics library for variogram analysis, kriging, and simulation. Use when the agent needs to: (1) Calculate experimental variograms, (2) Fit variogram models, (3) Perform simple/ordinary kriging, (4) Run sequential Gaussian simulation (SGSIM), (5) Apply normal score transforms, (6) Decluster spatial data, (7) Generate multiple realizations for uncertainty.",
  159. "version": "1.0.1"
  160. },
  161. {
  162. "name": "gnnwr",
  163. "source": "./",
  164. "strict": false,
  165. "skills": [
  166. "./gnnwr"
  167. ],
  168. "description": "Spatial and spatiotemporal regression with GNNWR (Geographically Neural Network Weighted Regression). Use when the agent needs to: (1) Build spatially varying coefficient regression models, (2) Analyze geographic non-stationarity in spatial data, (3) Generate spatial coefficient maps for publication, (4) Run spatiotemporal regression with GTNNWR, (5) Scale geographically weighted regression to large datasets (N > 10k) with KNN mode, (6) Diagnose spatial model performance with F-tests, AIC, and residual maps.",
  169. "version": "1.0.1"
  170. },
  171. {
  172. "name": "gprpy",
  173. "source": "./",
  174. "strict": false,
  175. "skills": [
  176. "./gprpy"
  177. ],
  178. "description": "Read and process ground-penetrating radar profiles using GPRPy. Use for sample-based dewow/background removal, auditable gain, time/depth scenarios, and radargram export with explicit acquisition units. SEG-Y input uses a separate segyio adapter; native GPRPy files are serialized sessions.",
  179. "version": "1.0.2"
  180. },
  181. {
  182. "name": "harmonica",
  183. "source": "./",
  184. "strict": false,
  185. "skills": [
  186. "./harmonica"
  187. ],
  188. "description": "Gravity and magnetic data processing and forward modelling using Fatiando a Terra. Use when the agent needs to: (1) Compute gravity forward models (point masses, prisms, tesseroids), (2) Apply terrain/Bouguer corrections, (3) Grid scattered potential field data with equivalent sources, (4) Perform upward/downward continuation, (5) Calculate magnetic anomalies from magnetized bodies, (6) Apply derivative filters (gradients, tilt angle), (7) Process regional or local gravity surveys.",
  189. "version": "1.0.1"
  190. },
  191. {
  192. "name": "hydrogeological-analysis",
  193. "source": "./",
  194. "strict": false,
  195. "skills": [
  196. "./workflows/hydrogeological-analysis"
  197. ],
  198. "description": "Combine groundwater observations, well logs, and meteorological stresses into a checked hydrogeological interpretation or groundwater-level model. Use for aquifer monitoring and recharge/pumping response analysis, with spatial flow modelling only when its geometry and boundary data are available.",
  199. "version": "1.0.1"
  200. },
  201. {
  202. "name": "landlab",
  203. "source": "./",
  204. "strict": false,
  205. "skills": [
  206. "./landlab"
  207. ],
  208. "description": "Landscape evolution and surface process modelling in Python. Build 2D numerical models for erosion, hydrology, soil transport, and geomorphology. Use when the agent needs to: (1) Model landscape evolution over time, (2) Simulate river/stream erosion, (3) Route water flow across terrain, (4) Model hillslope diffusion processes, (5) Simulate weathering and soil production, (6) Analyze drainage networks, (7) Combine multiple geomorphic processes, (8) Load/save DEM data for modeling.",
  209. "version": "1.0.1"
  210. },
  211. {
  212. "name": "lasio",
  213. "source": "./",
  214. "strict": false,
  215. "skills": [
  216. "./lasio"
  217. ],
  218. "description": "Read, write, and manipulate LAS (Log ASCII Standard) well log files for borehole geophysical and petrophysical data. Use when the agent needs to: (1) Read/parse LAS 1.2 or 2.0 files, (2) Extract well headers or curve data, (3) Convert LAS to DataFrame/CSV/Excel, (4) Create new LAS files from arrays, (5) Modify existing LAS files, (6) Handle problematic or malformed LAS files, (7) Batch process multiple well files.",
  219. "version": "1.0.2"
  220. },
  221. {
  222. "name": "loopstructural",
  223. "source": "./",
  224. "strict": false,
  225. "skills": [
  226. "./loopstructural"
  227. ],
  228. "description": "Build 3D geological models with implicit surfaces, faults, folds, and stratigraphic constraints from structural geology data. Use when the agent needs to: (1) Build 3D geological models from structural data, (2) Model fault networks and displacements, (3) Create folded geology representations, (4) Interpolate geological surfaces, (5) Export models to VTK for visualization, (6) Perform uncertainty analysis on geological models, (7) Evaluate model values on grids.",
  229. "version": "1.0.2"
  230. },
  231. {
  232. "name": "mplstereonet",
  233. "source": "./",
  234. "strict": false,
  235. "skills": [
  236. "./mplstereonet"
  237. ],
  238. "description": "Stereonet plots for structural geology using matplotlib. Create lower-hemisphere stereographic projections for orientation data. Use when the agent needs to: (1) Create stereonet plots for structural data, (2) Plot planes as great circles or poles, (3) Plot lineations with trend/plunge, (4) Generate density contours for orientations, (5) Calculate mean orientations and statistics, (6) Analyze fold axes with pi-diagrams, (7) Convert between strike/dip and trend/plunge formats.",
  239. "version": "1.0.1"
  240. },
  241. {
  242. "name": "mtpy",
  243. "source": "./",
  244. "strict": false,
  245. "skills": [
  246. "./mtpy"
  247. ],
  248. "description": "Read and validate magnetotelluric transfer functions with MTpy-v2. Use for EDI import, impedance uncertainty, apparent resistivity/phase, documented tensor rotations, response plots and preparation for modelling. External inversion solvers and raw time-series processing require separate tools and validation.",
  249. "version": "1.0.2"
  250. },
  251. {
  252. "name": "near-surface-geophysics",
  253. "source": "./",
  254. "strict": false,
  255. "skills": [
  256. "./workflows/near-surface-geophysics"
  257. ],
  258. "description": "Plan and validate near-surface interpretation from GPR, electrical resistivity tomography, or magnetotelluric data. Use when selecting acquisition-dependent processing and inversion branches, comparing survey results, or relating geophysical anomalies to independently supported geological hypotheses.",
  259. "version": "1.0.1"
  260. },
  261. {
  262. "name": "obspy",
  263. "source": "./",
  264. "strict": false,
  265. "skills": [
  266. "./obspy"
  267. ],
  268. "description": "Seismology data processing with ObsPy. Helps with reading seismic waveforms, filtering/processing time series, fetching data from FDSN services, and earthquake analysis. Use when the agent needs to: (1) Read seismic data formats (MiniSEED, SAC, GSE2, SEGY), (2) Filter or process waveforms, (3) Fetch data from IRIS/USGS/FDSN services, (4) Search for earthquakes by magnitude/location, (5) Plot seismograms or spectrograms, (6) Remove instrument response, (7) Analyze station metadata.",
  269. "version": "1.0.1"
  270. },
  271. {
  272. "name": "pastas",
  273. "source": "./",
  274. "strict": false,
  275. "skills": [
  276. "./pastas"
  277. ],
  278. "description": "Groundwater time series analysis and modelling using transfer function noise models. Use when the agent needs to: (1) Analyze groundwater level time series, (2) Model well responses to precipitation/pumping, (3) Calibrate aquifer parameters from head data, (4) Forecast or hindcast groundwater levels, (5) Decompose hydrological signals into components, (6) Compare response functions, (7) Perform model diagnostics and uncertainty analysis.",
  279. "version": "1.0.2"
  280. },
  281. {
  282. "name": "petropy",
  283. "source": "./",
  284. "strict": false,
  285. "skills": [
  286. "./petropy"
  287. ],
  288. "description": "Configure PetroPy fluid-property and multimineral formation evaluation from normalized LAS well logs. Use for calibrated porosity, water saturation, mineral and pore-volume estimation, missing-sample handling, and explicitly defined pay intervals. Requires documented log units, fluid parameters and mineral endpoints; standalone permeability correlations need separate methods.",
  289. "version": "1.0.2"
  290. },
  291. {
  292. "name": "pooch",
  293. "source": "./",
  294. "strict": false,
  295. "skills": [
  296. "./pooch"
  297. ],
  298. "description": "Data file fetching and caching for geoscience applications. Download sample datasets with automatic caching, checksum verification, and multiple download sources. Use when the agent needs to: (1) Download datasets from URLs or DOIs, (2) Cache files locally with automatic verification, (3) Verify file integrity with SHA256/MD5 hashes, (4) Extract compressed archives (ZIP, TAR, GZIP), (5) Create data registries for reproducible workflows, (6) Fetch from Zenodo or other repositories.",
  299. "version": "1.0.1"
  300. },
  301. {
  302. "name": "pygimli",
  303. "source": "./",
  304. "strict": false,
  305. "skills": [
  306. "./pygimli"
  307. ],
  308. "description": "Multi-method geophysical modelling and inversion framework. Use when the agent needs to: (1) Perform electrical resistivity tomography (ERT) inversion, (2) Run seismic refraction tomography (SRT), (3) Model induced polarization (IP) data, (4) Simulate ground penetrating radar (GPR), (5) Create finite element meshes for geophysical problems, (6) Perform joint inversions of multiple datasets, (7) Forward model geophysical responses, (8) Analyze time-lapse monitoring data.",
  309. "version": "1.0.1"
  310. },
  311. {
  312. "name": "pygmt",
  313. "source": "./",
  314. "strict": false,
  315. "skills": [
  316. "./pygmt"
  317. ],
  318. "description": "Make geographic maps and process geospatial grids with PyGMT and GMT, including projection, regions, grid registration and vector/raster export. Use for GMT cartography and map-ready scientific data; check the separate GMT shared library before plotting.",
  319. "version": "1.0.0"
  320. },
  321. {
  322. "name": "pyleoclim",
  323. "source": "./",
  324. "strict": false,
  325. "skills": [
  326. "./pyleoclim"
  327. ],
  328. "description": "Analyse paleoclimate proxy time series with Pyleoclim, including irregular sampling, spectra and comparisons across uncertain chronologies. Use for proxy Series and EnsembleSeries analysis, spectral peaks and age-model sensitivity; use xarray for gridded climate fields.",
  329. "version": "1.0.0"
  330. },
  331. {
  332. "name": "pylops",
  333. "source": "./",
  334. "strict": false,
  335. "skills": [
  336. "./pylops"
  337. ],
  338. "description": "Linear operators for large-scale inverse problems with matrix-free representations. Use when the agent needs to: (1) Define linear operators for forward/adjoint operations, (2) Solve inverse problems (deconvolution, imaging, tomography), (3) Apply signal processing transforms (FFT, convolution, derivatives), (4) Compose operators for complex workflows, (5) Perform regularized inversion with smoothness or sparsity constraints, (6) Process seismic or image data at scale.",
  339. "version": "1.0.1"
  340. },
  341. {
  342. "name": "pyrolite",
  343. "source": "./",
  344. "strict": false,
  345. "skills": [
  346. "./pyrolite"
  347. ],
  348. "description": "Geochemistry data analysis and visualization for igneous, metamorphic, and sedimentary rocks. Use when the agent needs to: (1) Create ternary diagrams for compositional data, (2) Plot REE spider diagrams with normalization, (3) Build TAS or other classification diagrams, (4) Apply log-ratio transforms to compositional data, (5) Calculate CIPW norms, (6) Generate Harker variation diagrams, (7) Compute element ratios and anomalies.",
  349. "version": "1.0.1"
  350. },
  351. {
  352. "name": "pyvista",
  353. "source": "./",
  354. "strict": false,
  355. "skills": [
  356. "./pyvista"
  357. ],
  358. "description": "3D visualization and mesh analysis for geoscience data using PyVista/VTK. Use when the agent needs to: (1) Create 3D visualizations of geological models, (2) Render seismic volumes or voxel data, (3) Visualize point clouds or well paths, (4) Plot surfaces and meshes in 3D, (5) Read/write VTK, STL, OBJ files, (6) Create cross-sections through 3D models, (7) Export publication-quality figures or interactive HTML.",
  359. "version": "1.0.1"
  360. },
  361. {
  362. "name": "rock-physics-avo",
  363. "source": "./",
  364. "strict": false,
  365. "skills": [
  366. "./workflows/rock-physics-avo"
  367. ],
  368. "description": "Rock physics and AVO analysis workflow from well log preparation through elastic property calculation, fluid substitution, AVO modelling, and synthetic seismogram generation. Use when performing rock physics studies or AVO feasibility analysis.",
  369. "version": "1.0.2"
  370. },
  371. {
  372. "name": "rockhound",
  373. "source": "./",
  374. "strict": false,
  375. "skills": [
  376. "./rockhound"
  377. ],
  378. "description": "Maintain or migrate legacy RockHound geoscience dataset downloads, caches and loaders such as PREM. Use when an existing project imports RockHound; prefer maintained Ensaio fetchers for supported new dataset workflows.",
  379. "version": "1.0.0"
  380. },
  381. {
  382. "name": "scikit-gstat",
  383. "source": "./",
  384. "strict": false,
  385. "skills": [
  386. "./scikit-gstat"
  387. ],
  388. "description": "Estimate and diagnose variograms, perform ordinary kriging, and validate spatial interpolation with SciKit-GStat. Use for empirical or directional variograms, covariance-model comparison and kriging prediction/variance; use PyKrige or GSTools when the task requires universal kriging or external drift.",
  389. "version": "1.0.2"
  390. },
  391. {
  392. "name": "segyio",
  393. "source": "./",
  394. "strict": false,
  395. "skills": [
  396. "./segyio"
  397. ],
  398. "description": "Read, write, and manipulate SEG-Y seismic data files. Fast C library with Python bindings for trace, header, inline, and crossline access. Use when the agent needs to: (1) Read/inspect SEG-Y files, (2) Extract trace data or headers, (3) Access 3D survey data by inline/crossline, (4) Create new SEG-Y files from arrays, (5) Modify existing SEG-Y files, (6) Extract subsets of seismic data, (7) Read/write Seismic Unix format.",
  399. "version": "1.0.2"
  400. },
  401. {
  402. "name": "segysak",
  403. "source": "./",
  404. "strict": false,
  405. "skills": [
  406. "./segysak"
  407. ],
  408. "description": "Read SEG-Y as labelled xarray datasets with SEGY-SAK, inspect header-defined survey dimensions and process seismic volumes lazily. Use for SEG-Y/xarray/Dask workflows; use segyio for exact low-level trace and header editing.",
  409. "version": "1.0.0"
  410. },
  411. {
  412. "name": "seismic-interpretation",
  413. "source": "./",
  414. "strict": false,
  415. "skills": [
  416. "./workflows/seismic-interpretation"
  417. ],
  418. "description": "End-to-end seismic interpretation workflow from SEG-Y loading through signal processing, rock physics, and visualization. Use when working with seismic data analysis pipelines.",
  419. "version": "1.0.2"
  420. },
  421. {
  422. "name": "simpeg",
  423. "source": "./",
  424. "strict": false,
  425. "skills": [
  426. "./simpeg"
  427. ],
  428. "description": "Simulation and Parameter Estimation in Geophysics. Framework for geophysical forward modeling and inversion. Use when the agent needs to: (1) Run geophysical inversions (DC resistivity, magnetics, gravity, EM), (2) Create forward models for potential fields or electromagnetic methods, (3) Build survey geometries and receiver configurations, (4) Design mesh discretizations for simulations, (5) Apply regularization and optimization to inverse problems, (6) Model subsurface physical properties from geophysical data.",
  429. "version": "1.0.1"
  430. },
  431. {
  432. "name": "striplog",
  433. "source": "./",
  434. "strict": false,
  435. "skills": [
  436. "./striplog"
  437. ],
  438. "description": "Create, visualize, and analyze lithological and stratigraphic logs for well data. Use when the agent needs to: (1) Create lithology columns from depth intervals, (2) Parse geological descriptions into structured logs, (3) Visualize stratigraphic columns with patterns and colors, (4) Perform well-to-well correlations, (5) Extract statistics like net-to-gross ratios, (6) Define rock type lexicons and legends, (7) Export lithology data to CSV/LAS/JSON.",
  439. "version": "1.0.1"
  440. },
  441. {
  442. "name": "using-geoscience-skills",
  443. "source": "./",
  444. "strict": false,
  445. "skills": [
  446. "./using-geoscience-skills"
  447. ],
  448. "description": "Discover and compose geoscience skills for Python coding tasks. Use when choosing a geoscience library, finding a skill for a data format or method, or planning work across seismic, well logs, geological modelling, inversion, and other geoscience domains.",
  449. "version": "1.0.2"
  450. },
  451. {
  452. "name": "verde",
  453. "source": "./",
  454. "strict": false,
  455. "skills": [
  456. "./verde"
  457. ],
  458. "description": "Spatial data gridding and interpolation with a machine-learning style API. Process geographic and Cartesian point data onto regular grids. Use when the agent needs to: (1) Grid scattered spatial data onto regular grids, (2) Interpolate point data using splines, linear, or cubic methods, (3) Process geographic coordinates with projections, (4) Reduce large datasets using block averaging, (5) Remove polynomial trends from spatial data, (6) Cross-validate gridding parameters, (7) Create processing pipelines with Chain, (8) Grid vector data like GPS velocities.",
  459. "version": "1.0.1"
  460. },
  461. {
  462. "name": "well-log-evaluation",
  463. "source": "./",
  464. "strict": false,
  465. "skills": [
  466. "./workflows/well-log-evaluation"
  467. ],
  468. "description": "Complete well log evaluation workflow from LAS/DLIS loading through QC, petrophysical analysis, lithology classification, and visualization. Use when performing formation evaluation from well log data.",
  469. "version": "1.0.2"
  470. },
  471. {
  472. "name": "welly",
  473. "source": "./",
  474. "strict": false,
  475. "skills": [
  476. "./welly"
  477. ],
  478. "description": "Subsurface well data analysis toolkit for loading, processing, and analyzing well logs, projects, and formation tops. Built on lasio with enhanced curve processing. Use when the agent needs to: (1) Load wells from LAS files with metadata, (2) Work with multi-well Projects, (3) Process curves (despike, smooth, resample, normalize), (4) Manage formation tops, (5) Export well data to DataFrame/LAS/CSV, (6) Perform cross-well analysis and QC.",
  479. "version": "1.0.2"
  480. },
  481. {
  482. "name": "xarray",
  483. "source": "./",
  484. "strict": false,
  485. "skills": [
  486. "./xarray"
  487. ],
  488. "description": "N-dimensional labeled arrays for geoscience data. Read/write NetCDF, work with climate and oceanographic datasets, perform multi-dimensional analysis with labeled coordinates. Use when the agent needs to: (1) Read/write NetCDF or Zarr files, (2) Work with multidimensional arrays with labeled dimensions, (3) Analyze climate, ocean, or atmosphere data, (4) Compute temporal aggregations (daily/monthly/annual means), (5) Perform area-weighted statistics, (6) Process large datasets with Dask, (7) Apply CF conventions to scientific data.",
  489. "version": "1.0.1"
  490. }
  491. ]
  492. }
README.md · README · 273 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # 🌍 Geoscience Skills
  2. **Portable geoscience skills for Codex, Claude Code, GitHub Copilot, Gemini CLI, Windsurf, OpenCode, Cline, Roo Code, OpenClaw, and other coding agents using the [Agent Skills format](https://agentskills.io/specification).**
  3. 39 domain skills + 8 workflows + 1 discovery skill. The same skill files are shared across agents; platform commands, hooks, and subagents are optional. See the [verification results](#verification-results) and [compatibility matrix](docs/COMPATIBILITY.md).
  4. [![Skills](https://img.shields.io/badge/Skills-48-blue)](SKILLS.md)
  5. [![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
  6. ---
  7. ## 🎯 Capabilities at a Glance
  8. | Domain | What You Can Do |
  9. |--------|-----------------|
  10. | **🔬 Seismic** | Read SEG-Y files, process waveforms, fetch earthquake data, compute dispersion curves |
  11. | **🛢️ Well Logs** | Parse LAS/DLIS files, calculate porosity & saturation, create striplogs |
  12. | **🏔️ 3D Modelling** | Build implicit geological models with faults and folds |
  13. | **📡 Inversion** | Run ERT, seismic, gravity, magnetic inversions |
  14. | **🗺️ Geostatistics** | Variograms, kriging, spatial interpolation, gridding |
  15. | **🌊 Climate/Ocean** | NetCDF analysis, multi-dimensional arrays, time series |
  16. | **💧 Hydrology** | Groundwater modelling, landscape evolution |
  17. | **🧪 Geochemistry** | REE patterns, spider diagrams, classification plots |
  18. | **📊 Visualization** | 3D mesh rendering, stereonets, publication figures |
  19. ---
  20. ## ⚡ Quick Examples
  21. ```
  22. "Read this SEG-Y file and show the first 10 traces"
  23. "Calculate water saturation from these well logs using Archie equation"
  24. "Build a 3D geological model with two faulted horizons"
  25. "Invert this ERT survey and plot the resistivity section"
  26. "Compute variogram and run kriging on this spatial data"
  27. "Load this NetCDF climate file and compute monthly anomalies"
  28. "Create a chondrite-normalized REE spider diagram"
  29. ```
  30. ---
  31. ## 📦 Installation
  32. ### Upstream skills CLI (recommended)
  33. Run from the project where you want to use the skills. The installer supports
  34. multiple coding agents and manages their destination directories.
  35. ```bash
  36. # Inspect all domain, workflow, and routing skills
  37. npx skills add SteadfastAsArt/geoscience-skills --full-depth --list
  38. # Select skills and target agents interactively
  39. npx skills add SteadfastAsArt/geoscience-skills --full-depth
  40. # Install a starting set for multiple agents
  41. npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  42. --skill using-geoscience-skills lasio segyio --agent codex claude-code
  43. # Install the whole collection for one agent
  44. npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  45. --skill '*' --agent gemini-cli
  46. # Install a workflow and the domain skills needed for it
  47. npx skills add SteadfastAsArt/geoscience-skills --full-depth \
  48. --skill well-log-evaluation lasio dlisio welly petropy striplog pyvista \
  49. --agent github-copilot
  50. ```
  51. Keep `--full-depth` to include workflows nested under `workflows/`. Add `--global`
  52. for user scope; use `--copy` if you prefer copies to symlinks. Choosing a workflow
  53. does not automatically install its complementary skills or Python dependencies.
  54. Other targets include `windsurf`, `opencode`, `cline`, `roo`, and `openclaw`;
  55. consult the [upstream supported-agent list](https://github.com/vercel-labs/skills#supported-agents).
  56. ```bash
  57. npx skills list
  58. # Explicitly update installed skills when desired
  59. npx skills update
  60. ```
  61. ### From a local checkout
  62. ```bash
  63. git clone https://github.com/SteadfastAsArt/geoscience-skills.git
  64. # Run this in your target project; replace the path with your checkout location.
  65. npx skills add /path/to/geoscience-skills --full-depth --agent codex
  66. ```
  67. For manual installation, copy each selected **skill directory** to a directory
  68. supported by your agent. Preserve its `SKILL.md`, `references/`, and `scripts/`.
  69. For a workflow, copy `workflows/<name>/` as `<name>/` alongside the domain skills.
  70. Do not copy the whole repository into an agent's skill directory. Platform
  71. configuration and optional role guides are separate from skill installation.
  72. See [platform notes and the manual reading fallback](docs/COMPATIBILITY.md).
  73. ### Python dependencies
  74. Install the packages needed for your task in its Python environment. For example:
  75. ```bash
  76. # LAS inspection and conversion
  77. python -m pip install lasio pandas
  78. # SEG-Y inspection and subsetting
  79. python -m pip install segyio numpy
  80. ```
  81. Skill `metadata.dependencies` records library requirements; installing a skill
  82. does not install or validate those packages. See [SKILLS.md](SKILLS.md) for
  83. additional domain-specific package lists.
  84. ---
  85. ## 🧠 39 Domain Skills
  86. ### By Domain
  87. ```
  88. Seismic & Seismology → obspy, segyio, segysak, disba
  89. Well Logs & Petrophysics → lasio, welly, dlisio, striplog, petropy
  90. 3D Geological Modelling → gempy, loopstructural, gemgis, geolime (licensed)
  91. Geophysical Inversion → simpeg, devito, pylops, pygimli, discretize
  92. Potential Fields → harmonica, boule
  93. Rock Physics → bruges
  94. Geostatistics → verde, geostatspy, scikit-gstat, gnnwr
  95. Hydrology → pastas, flopy
  96. Surface Processes → landlab
  97. Structural Geology → mplstereonet
  98. Geochemistry → pyrolite
  99. Near-surface Geophysics → gprpy, mtpy
  100. Data Formats → xarray (NetCDF/HDF5/Zarr), pyleoclim
  101. Visualization → pyvista, pygmt
  102. Datasets → pooch, ensaio, rockhound (legacy)
  103. ```
  104. > 📋 Full details: [SKILLS.md](SKILLS.md)
  105. ---
  106. ## 🔧 Usage
  107. Describe the task naturally, or select an installed skill using your agent's
  108. skill interface:
  109. - "Use lasio to inspect the headers and curves in this LAS file."
  110. - "Use well-log-evaluation to evaluate these logs."
  111. - "Use using-geoscience-skills to choose the tools for this task."
  112. The router selects domain and workflow skills by name. Workflows can run within
  113. one agent session and do not require a particular delegation tool. Only the
  114. references and workflow stages needed for the task should be loaded.
  115. Claude Code users working in this checkout can also use the optional aliases
  116. in `.claude/commands/`: `/seismic-workflow`, `/well-analysis`, `/model-3d`,
  117. `/inversion-workflow`, and `/spatial-gridding`. These aliases and the local
  118. SessionStart hook are not installed by the generic skills CLI.
  119. ---
  120. ## 📊 Coverage
  121. | Metric | Value |
  122. |--------|-------|
  123. | Installable Skills | 48 (39 domain + 8 workflow + 1 router) |
  124. | File Formats Supported | SEG-Y, LAS, DLIS, NetCDF, HDF5, Zarr, GRIB, VTK |
  125. The [per-skill validation matrix](docs/VALIDATION_MATRIX.md) records test scopes
  126. for all 48 skills. Of 39 bundled scripts, 16 have declared execution tests and
  127. 23 have explicit coverage gaps. A mapping does not establish a passing run or
  128. validate an entire library; native-task evidence is listed separately.
  129. ---
  130. ## Verification results
  131. Updated **2026-10-25**. [PR #3](https://github.com/SteadfastAsArt/geoscience-skills/pull/3)
  132. and the subsequent P1–P3 delivery in
  133. [PR #5](https://github.com/SteadfastAsArt/geoscience-skills/pull/5) are merged.
  134. The workflow follow-up extends their scientific evidence; native Agent runs
  135. retain their original recorded revisions.
  136. | Check | Recorded result |
  137. | --- | --- |
  138. | Native Codex tasks | **LAS QC, SEG-Y subsetting and formation evaluation passed** without task prompts naming skills or catalog paths. Each run discovered all 48 skills and retained successful native skill-read evidence. See [agent evaluations](docs/AGENT_EVALUATIONS.md). |
  139. | Installation | **48 skills × nine targets passed locally** with skills CLI 1.5.26, including bundled resources. Linux/Windows CI runs the same checks; see [compatibility evidence](docs/COMPATIBILITY.md#verification-scope). |
  140. | September automated baseline | **268 checks**: 204 scientific across ten isolated environments, 61 lightweight and 3 evaluation-fixture readbacks. See [dated results and reproduction](docs/SCIENTIFIC_TESTING.md). |
  141. | October local follow-up | **12 SciKit-GStat scientific tests and 74 lightweight tests passed**. Added an eleventh isolated environment, coverage inventory gate and scientific runner that fails skipped tests. Current inventory is 293 tests; the other scientific environments and native agent tasks were not rerun in this follow-up. [Scope and commands](docs/SCIENTIFIC_TESTING.md). |
  142. | Field data | Published well logs, earthquake waveform and ERT observations now join GNSS, with licenses, units, holdout checks and explicit uncertainty limits. See [field-data validation](docs/FIELD_DATA_VALIDATION.md). |
  143. | Workflow execution | Groundwater head/stress data → Pastas hindcast; GPR/ERT/MT → checked processing or model diagnostics; NOAA TMAX → labelled climate outputs. Independent numerical, holdout and output-readback checks are recorded in the [hydro](docs/HYDRO_WORKFLOW_VALIDATION.md), [near-surface](docs/NEAR_SURFACE_WORKFLOW_VALIDATION.md) and [climate](docs/CLIMATE_WORKFLOW_VALIDATION.md) reports. |
  144. | Dependencies | Candidate NumPy/SciPy updates passed; incompatible pandas/setuptools combinations were rejected. The [report workflow ran successfully on main](https://github.com/SteadfastAsArt/geoscience-skills/actions/runs/34854160260). See [decisions](docs/DEPENDENCY_MAINTENANCE.md). |
  145. Claude runtime testing is excluded from this round. Other client availability
  146. and optional-adapter decisions are in the [platform assessment](docs/PLATFORM_ADAPTER_ASSESSMENT.md).
  147. Scientific execution is verified on Linux. GeoLime requires a licensed vendor
  148. runtime; RockHound is maintained here for legacy migration, with its failed
  149. upstream PREM URL documented. The [new collection report](docs/COLLECTION_VALIDATION.md)
  150. distinguishes the executed workflow cases from remaining field-calibration,
  151. sampling-metadata, joint-inversion and forecasting limits.
  152. ---
  153. ## 🔄 Workflow Skills
  154. Multi-step workflows that chain domain skills together:
  155. | Workflow | Skills Used | Use Case |
  156. |----------|------------|----------|
  157. | Seismic Interpretation | segyio → obspy → bruges → pyvista | Seismic data analysis |
  158. | Well Log Evaluation | lasio/dlisio → welly → petropy → striplog | Formation evaluation |
  159. | Geological Modelling | gemgis → gempy/loopstructural → pyvista | 3D model building |
  160. | Geophysical Inversion | simpeg/pygimli → verde → pyvista | ERT, magnetics, gravity |
  161. | Rock Physics & AVO | lasio/welly → bruges → segyio | AVO feasibility studies |
  162. | Hydrogeological Analysis | well logs + pastas; optional flopy | Groundwater head and aquifer hypotheses |
  163. | Near-surface Geophysics | gprpy + pygimli/simpeg + mtpy | Compare GPR, ERT and MT evidence |
  164. | Climate Analysis | xarray + verde; optional pyleoclim | Time/space analysis without validation leakage |
  165. The audited examples have separate [scientific regression checks](docs/SCIENTIFIC_TESTING.md)
  166. using generated LAS/SEG-Y files, elastic logs, geological/inversion models, and
  167. [published field data](docs/FIELD_DATA_VALIDATION.md). These check numerical
  168. outputs, coordinates and uncertainty assumptions. Recorded [Codex task evaluations](docs/AGENT_EVALUATIONS.md)
  169. separately check skill selection and produced files.
  170. ## 🤖 Optional Role Guides
  171. The files in `agents/` provide optional role guidance. A generic skill installation
  172. does not register them as subagents; use them explicitly when available.
  173. | Guide | Role |
  174. |-------|------|
  175. | data-qc-reviewer | Check well log, seismic, and spatial data quality |
  176. | geoscience-mentor | Guide skill and workflow selection |
  177. | cross-validation-reviewer | Review independent holdouts, uncertainty and model comparison |
  178. ---
  179. ## 🤝 Contributing
  180. PRs welcome! See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full guide, including:
  181. - Step-by-step instructions for adding a new skill
  182. - Portable frontmatter and project metadata conventions
  183. - Task boundaries, resource loading, and scientific validation guidance
  184. - Recursive skill validation, generated platform manifests, and installation smoke tests
  185. See **[docs/ROADMAP.md](docs/ROADMAP.md)** for completed priorities and remaining validation boundaries.
  186. [Dependency maintenance](docs/DEPENDENCY_MAINTENANCE.md) describes the weekly
  187. registry report and the checks required before adopting new library or installer versions.
  188. ---
  189. ## 📚 Resources
  190. - **Source**: [awesome-open-geoscience](https://github.com/softwareunderground/awesome-open-geoscience)
  191. - **Skills Spec**: [Agent Skills specification](https://agentskills.io/specification)
  192. - **Community**: [Software Underground](https://softwareunderground.org/)
  193. ---
  194. ## 📄 License
  195. MIT © 2024
  196. Bundled data retain their own licenses and attribution:
  197. - [Alps GNSS](tests/fixtures/field/alps_gps/ATTRIBUTION.md): original CC BY 3.0 and curated CC BY 4.0.
  198. - [Published well logs](tests/fixtures/field/well_logs/ATTRIBUTION.md): CC BY 4.0.
  199. - [GEOFON waveform and response](tests/fixtures/field/seismic_waveform/ATTRIBUTION.md): CC BY 4.0.
  200. - [Crescentino ERT](tests/fixtures/field/ert_survey/ATTRIBUTION.md): CC BY 4.0.
  201. Project-generated audit fixtures are explicitly synthetic and do not represent
  202. field observations.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.