s2s-forecasting-expert
by manmeet3591
CLI UtilitiesBrief
End-to-end builder for AI-based Subseasonal-to-Seasonal (S2S) forecasting systems.
Description
What This Skill Does
Generates runnable PyTorch code for Subseasonal-to-Seasonal (S2S) weather forecasting systems. Covers model architectures inspired by FuXi, FengWu, and AIFS, plus training loops, CRPS loss, and evaluation scripts. All code runs locally with no external API calls.
Provides domain-specific architecture patterns and loss functions for S2S forecasting that general code assistants rarely get right without extensive prompting.
When to Use It
- Building a FuXi-style transformer for 30-day Z500 forecasting
- Implementing CRPS loss for probabilistic ensemble outputs
- Scaffolding an ERA5 data preprocessing and training pipeline
- Setting up distributed multi-GPU training for global grid models
- Generating evaluation scripts comparing model skill against climatology
Example Workflow
User asks: Generate a FuXi-style transformer in PyTorch for 30-day Z500 forecasting with CRPS loss
- 1
Designs a 3D spatiotemporal transformer architecture with global grid attention
- 2
Generates multi-variable input pipeline handling Z500, T2M, and wind fields
- 3
Implements lead-time conditioned decoder with ensemble output heads
- 4
Creates CRPS loss function in both Gaussian and ensemble forms
- 5
Outputs training loop with mixed precision and checkpoint saving
Complete PyTorch module files for model, loss, and training loop ready to run locally
Installation
clawhub install manmeet3591/s2s-forecasting-expertRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.