claude

dsm-soil

12 soil-science skills forged from the DSM knowledge wiki: soil quality & health indexing (SQI/SHI — minimum data set, indicator scoring, weighting, aggregation, validation, SEM, fuzzy rules), fertility mapping, prediction uncertainty (AOA/LPD/Monte-Carlo), sampling design, ML for soil, ensemble ML (whether to combine models at all — the ambiguity ceiling, the weighting spectrum, cross-fitted combiners), end-to-end DSM workflow, map validation, RothC temporal modelling, hybrid process+ML SOC, SOC-stock MRV, and spatial statistics on areal data (Moran/LISA/BiLISA, SAR/SEM/SDM/SDEM, spillover impacts) with verified R and Python pipelines.

13 on GitHubby Carbajalv0.6.1MITupdated 20 days ago
/

Plugin dsm-soil from marketplace soil-dsm-skills in ccarbajal16/soil-dsm-skills. Commands read from the repo's manifest — 20 days ago.

What it installs

Skills (12)

  • digital-soil-mapping-workflow

    Run a digital soil mapping (DSM) project end to end — from framing the target and assembling scorpan covariates, through sampling design, model selection, handling spatial autocorrelation, training, and producing a map with calibrated uncertainty. Use when planning or reviewing any project that pred

  • ensemble-ml-for-soil

    Decide whether to combine machine-learning models at all, and if so how — by measuring the gain available before building any combiner. Covers the ambiguity/diversity ceiling, the weighting spectrum (simple average, R²-weighted, Bates–Granger, AIC/BIC, NNLS/SuperLearner, Granger–Ramanathan, learned

  • hybrid-process-ml-soc

    Design and build hybrid soil-organic-carbon models that fuse a process-oriented model (RothC / CENTURY / Millennial) with machine learning (Random Forest / QRF) to predict SOC stock in space AND time — getting ML's spatial accuracy together with the process model's physically-plausible temporal dyna

  • ml-for-soil-prediction

    Choose, tune, and reason about machine-learning models for predicting soil properties (SOC, texture, pH, …) — Random Forest, Quantile Regression Forests, gradient boosting, and deep learning — including per-pixel uncertainty and interpretability. Use when the task is the ML modelling craft itself: w

  • rothc-temporal-modelling

    Set up, initialize, calibrate, validate, and interpret the RothC (Rothamsted Carbon) model — and CENTURY-family process models — for simulating soil organic carbon stock and its change over time. Use when modelling SOC dynamics under management or climate scenarios, initializing RothC pools (spin-up

  • soc-stock-mrv

    Quantify, report, and verify soil-organic-carbon stock and its change over time for carbon markets / MRV (Monitoring, Reporting, Verification) — computing SOC stock, estimating change and its uncertainty at the field/project support, and applying the uncertainty deduction that determines creditable

  • soil-fertility-mapping

    Produce national/regional maps of multiple soil fertility properties and nutrients from harmonized legacy data with machine learning, and integrate them into a composite Soil Fertility Index (SFI) with honest, propagated uncertainty. Use when the goal is a multi-property fertility product (texture,

  • soil-map-validation

    Validate soil property maps and SOC (organic carbon) predictions rigorously — choosing cross-validation strategy, computing and interpreting accuracy metrics, checking that uncertainty is honest, and aggregating uncertainty to the reporting support. Use when reviewing, designing, or reporting the ac

  • soil-quality-index

    Build, validate and interpret a Soil Quality Index (SQI) or Soil Health Index (SHI) from measured soil indicators — selecting a minimum data set, scoring indicators, weighting and aggregating them, and proving the index actually discriminates. Covers land-use and management comparison, degradation q

  • soil-sampling-design

    Choose and design a soil sampling scheme for digital soil mapping — where (and when) to sample, how many, and by which method — matched to the objective (feature-space vs spatial coverage, representativeness, local heterogeneity, multiple properties, cost/accessibility, space-time) and to whether yo

  • spatial-prediction-uncertainty

    Quantify, map, and communicate the uncertainty of a spatial ML prediction on BOTH axes — distributional ("how variable is the outcome here?") and epistemic coverage ("has the model even seen anything like here?"). Use when you need honest per-pixel uncertainty for a digital soil map, nutrient/fertil

  • spatial-statistics-areal

    Analyse spatial association and spatial dependence on areal (lattice/polygon) data for ANY variable — global and local Moran's I, LISA hot/cold spots and spatial outliers, bivariate Moran and BiLISA, Lee's L, spatial weights matrices and their robustness, Rao's-score (ex-Lagrange multiplier) diagnos

View source on GitHub

Similar plugins

Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams

26 skills · 4 commands · 3 agents · 1 MCP server

anthropics/claude-plugins-official 47,076

Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.

1 skill · 3 commands · 1 agent

alirezarezvani/claude-skills 29,725

Data engineering, ML, and AI specialists - data pipelines, machine learning, LLM architecture

VoltAgent/awesome-claude-code-subagents 26,513

Operator-grade Mistral skill pack with 24 current API, security, reliability, governance, and migration workflows

24 skills

jeremylongshore/tons-of-skills-marketplace 2,917

View, search, download, and read academic papers from arXiv. Supports API queries, web scraping via Actionbook, and HTML paper reading via ar5iv.

1 skill · 10 commands · 5 agents · 1 MCP server

actionbook/actionbook 1,630

AI-first computer-science conference skill stack: 155 conference fit-and-submission profiles plus a CS/AI router. Covers top AI/ML, data mining, vision, NLP, robotics, HCI, systems, security, software engineering, programming languages, databases, and theory venues, with current-cycle CFP and author-kit re-check discipline.

156 skills

brycewang-stanford/Awesome-Journal-Skills 1,413

Maintain dsm-soil?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted