playbooks

home / skills / omer-metin / skills-for-antigravity / climate-modeling

climate-modeling skill

/skills/climate-modeling

This skill helps you analyze climate data and run CMIP6 based projections, enabling downscaling, scenario assessment, and impact insights.

npx playbooks add skill omer-metin/skills-for-antigravity --skill climate-modeling

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
1.2 KB
---
name: climate-modeling
description: Work with climate data, models, and projections for climate impact assessment, downscaling, and scenario analysis using CMIP6 and other climate datasets. Use when "climate model, climate projection, CMIP6, climate data, downscaling, climate scenario, RCP, SSP, global warming, " mentioned. 
---

# Climate Modeling

## Identity



## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill helps analysts and researchers work with climate data, models, and projections for impact assessment, downscaling, and scenario analysis. It focuses on CMIP6 and other common climate datasets and enforces reproducible patterns and strict validation to reduce modeling errors. The skill is implemented in Python and designed for practical workflows: data ingestion, bias correction, downscaling, and scenario-based projection.

How this skill works

The skill inspects input datasets, metadata, and user-specified scenarios, then applies established construction patterns for datasets and models. It uses a diagnostics module to detect sharp-edge failure modes and a validation layer to enforce constraints and data integrity before producing projections or downscaled outputs. When conflicts arise, it explains risks and recommends safe alternatives grounded in the reference patterns and validations.

When to use it

  • Preparing CMIP6 data for impact assessment or sectoral modeling
  • Running bias correction and statistical downscaling workflows
  • Comparing RCP/SSP scenario projections across models
  • Validating climate model inputs against strict quality rules
  • Diagnosing unexpected model outputs or projection anomalies

Best practices

  • Always start by validating metadata and temporal coverage before processing
  • Follow the provided construction pattern for reproducible dataset builds
  • Run the diagnostic checks to catch common sharp-edge failure modes early
  • Document scenario choices, assumptions, and any interpolations applied
  • Use conservative extrapolation and flag areas with insufficient observational coverage

Example use cases

  • Downscale CMIP6 temperature and precipitation for a regional hydrology model
  • Perform multi-model ensemble analysis across SSP scenarios for emission-impact studies
  • Detect and correct systematic biases before feeding projections into impact models
  • Validate incoming climate data against schema rules and temporal consistency checks
  • Produce reproducible scenario bundles with provenance for policy reporting

FAQ

What datasets and scenarios does the skill support?

It is built for CMIP6 and common climate datasets and supports standard scenario families like SSPs and RCP-equivalent mappings; custom scenario inputs are allowed if they pass validation.

How does the skill prevent modeling errors?

It enforces construction patterns, runs diagnostics that surface known sharp-edge failures, and applies strict validations to inputs and outputs before producing final projections.