Earth and space system models,
packaged for AI agents.

Earth-Space-Modeling-skills is a collection of skill packages for Earth, planetary, and space science models.Each repo is a self-contained, progressive-disclosure knowledge package: a SKILL.md routing hub plus reference/ deep-dive docs covering install, compile, run, modify, debug, and contribute.Designed to be loaded as skills by AI coding agents (Claude Code, Codex, Cursor) and to serve as durable, human-readable references for researchers and developers.

— What this is

Procedural knowledge for Earth and space science, made loadable.

Mechanistic Earth-system models (CESM, E3SM, WRF, MOM6, Noah-MP, CTSM, JULES, ...) carry decades of accumulated scientific judgment in their source trees, build systems, and debug folklore. Most of that knowledge lives in PDFs, mailing lists, and the heads of senior researchers.

A skill repo is a structured, progressive-disclosure package of that knowledge: a routing hub (SKILL.md) for top-level intent, and a reference/ tree of deep-dive docs by topic (architecture, physics, workflow, debugging, ...). It is designed to be loaded into an agent's context on demand and to stay readable as a human reference.

Each repo carries its own license. Each is maintained alongside the model it covers. We currently host 28 skill repos across Earth-system, atmosphere, land, ocean, sea-ice, and heliophysics domains.

— Models

Skill repos by domain.

Status legend: deep-dive complete. scaffold (v0.1.0-scaffold), routing and source-grounded surface verified, operational depth being filled in.

Earth-system / coupled

  • cam-skill, Community Atmosphere Model (CAM)
  • cesm-skill, Community Earth System Model (CESM) superproject
  • e3sm-skill, Energy Exascale Earth System Model (E3SM)
  • noresm-skill, Norwegian Earth System Model (NorESM)
  • fms-skill, GFDL Flexible Modeling System (FMS) framework

Atmosphere

Land surface and hydrology

  • noahmp-skill, Noah-MP land surface model and HRLDAS
  • ctsm-skill, Community Terrestrial Systems Model (CTSM/CLM)
  • jules-skill, Joint UK Land Environment Simulator (JULES)
  • summa-skill, Structure for Unifying Multiple Modeling Alternatives (SUMMA)
  • vic-skill, Variable Infiltration Capacity (VIC) macroscale hydrologic model
  • parflow-skill, ParFlow parallel watershed flow model

Ocean

Sea ice

— Partner skill repos

Maintained by collaborators, part of the broader effort.

These repos live in their authors' own namespaces. They follow the same progressive-disclosure skill pattern and ship alongside the core org.

Heliophysics / space physics models

  • laps-skill (by @huangzesen), LingTai progressive-disclosure skill for LAPS, the UCLA-Pseudo-Spectral 3D Hall-MHD Fortran code.
  • lingtai-batsrus-skill (by @huangzesen), Skill for BATS-R-US, the Block-Adaptive Tree Solar-wind Roe-type Upwind Scheme MHD solver at the core of SWMF.

Heliophysics observation / data access

  • xhelio-cdaweb (by @huangzesen), NASA CDAWeb data access for heliophysics: MCP server + Python library.
  • xhelio-spice (by @huangzesen), SPICE toolkit access for heliophysics.
  • xhelio-pds (by @huangzesen), NASA PDS (Planetary Data System) access for heliophysics.
— Anatomy

Layout of a skill repo.

<model>-skill/
├── SKILL.md              # Routing hub: when to use, where to look
├── reference/            # Deep-dive docs by topic
│   ├── architecture.md
│   ├── physics.md
│   ├── workflow.md
│   ├── debugging.md
│   └── ...
└── README.md

Contribute.

Open an issue or PR on the relevant repo. For new model coverage that fits the scope (Earth, ocean, atmosphere, land, ice, space weather, planetary), open an issue on the org before starting a new repo.

Visit the GitHub org