Forecasts time series zero-shot with Google's TimesFM foundation models — TimesFM 2.5 (200M, Apache-2.0 weights; ForecastConfig API, XReg covariates) and TimesFM 3.0 (~330M, multivariate with native past/future covariates; non-commercial weights) — producing point forecasts and quantile prediction intervals from CSV/DataFrame/array inputs, with a preflight system checker for RAM/GPU.
安装
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-timesfmnpx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-timesfm -a claude-code -gnpx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-timesfm -a codex -ggemini skills install https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git --path skills/data-science/alterlab-timesfmgh skill install AlterLab-IEU/AlterLab-Academic-Skills alterlab-timesfmgit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-Skills /tmp/AlterLab-IEU__AlterLab-Academic-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/AlterLab-IEU__AlterLab-Academic-Skills/skills/data-science/alterlab-timesfm ~/.claude/skills/alterlab-timesfm # Claude Code
cp -R /tmp/AlterLab-IEU__AlterLab-Academic-Skills/skills/data-science/alterlab-timesfm ~/.agents/skills/alterlab-timesfm # Codex, Cursor, Gemini CLI, Copilot, OpenCode