How are price regimes classified?

The skill uses 12-26 week ROC momentum, linear regression slopes, and ATR volatility to categorize the market into Downtrend, Bottoming, Uptrend, or Overheat stages.

Can I use this for ETFs other than LIT?

While optimized for the Global X Lithium & Battery Tech ETF (LIT), the logic can be applied to any basket of lithium-related stocks by adjusting the input ticker and holdings structure.

How does this skill estimate lithium demand?

It converts GWh battery demand into Lithium Carbonate Equivalent (LCE) using three scenarios: Conservative (0.12 kg/kWh), Neutral (0.15 kg/kWh), and Aggressive (0.18 kg/kWh).

What data levels does the radar support?

It features a fallback strategy ranging from 'free_nolimit' (USGS/IEA/CME) to 'paid_high' (Fastmarkets/S&P/BNEF) depending on your available data access.

Lithium Supply-Demand Radar

Name: Lithium Supply-Demand Radar
Author: fatfingererr

byfatfingererr

0•

データサイエンスとML

Analyzes the lithium supply chain and price regimes to provide data-driven insights for commodity investments and ETF exposure.

This skill integrates complex data across the lithium lifecycle—from mining and refining to battery production and EV demand—into a unified analytical framework. It maps physical supply-demand gaps to financial instruments like the Global X Lithium & Battery Tech ETF (LIT), identifying price regimes such as 'bottoming' or 'overheat' and calculating rolling beta sensitivities. It is designed for macro-investors and commodity analysts who need to automate the extraction, normalization, and visualization of battery metal market trends using a multi-layered data fallback strategy.

主な機能

01Multi-layered supply chain analysis across upstream, midstream, and downstream sectors

02Automated 6-in-1 professional visualization dashboards for market inflection points

030 GitHub stars

04ETF transmission sensitivity analysis via 52-week rolling beta calculations

05Price regime classification using 12-26 week momentum and volatility metrics

06Automated lithium content conversion (LCE/GWh) with scenario-based modeling

ユースケース

01Identifying optimal entry and exit windows for lithium ETFs based on price cycle momentum

02Standardizing disparate data sources from USGS, IEA, and market providers into a single analytical pipeline

03Forecasting lithium supply-demand gaps based on real-time EV sales and battery installation data

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add fatfingererr/macro-skills lithium-supply-demand-gap-radar

For use in Claude.ai and ChatGPT

Download Skill