timesfm-forecasting
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series mod
npx skills add majiayu000/claude-skill-registry --skill timesfm-forecasting-foryourhealth111-pix-vibe-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Forecasts univariate time series without training a model, returning point forecasts and calibrated quantile intervals. Requires a preflight system checker before first use to verify RAM, GPU, and disk space, and adapts to input formats like CSV, DataFrame, or arrays. Includes optional covariate forecasting and anomaly-interval guidance via quantiles.
How it works
- Uses TimesFM as a zero-shot foundation model for time-series forecasting, wrapping local inference with safety checks.
- Runs a mandatory preflight script (python scripts/check_system.py) to verify available RAM, GPU, disk space, Python version, and existing installations before loading the model.
- Accepts inputs in CSV, DataFrame, or array formats and outputs a point forecast and a quantile forecast (10 quantiles, providing prediction intervals).
- Configurable via timesfm.ForecastConfig to control context window, horizon, normalization, batch sizing, and quantile handling (e.g., use_continuous_quantile_head, fix_quantile_crossing).
- Supports forecast_with_covariates for exogenous inputs and provides an anomaly-detection style interpretation using prediction intervals.
When to use it
- Forecasting any univariate time series with zero-shot capability (no training required).
- You require probabilistic forecasts with calibrated prediction intervals.
- You plan to batch-forecast many series efficiently or handle long context windows (up to model limits).
- You prefer a foundation-model approach over classical models like ARIMA when multivariate dependencies are not required.
What it can touch
- Tools allowed: Read, Write, Edit, Bash (through frontmatter). The workflow demonstrated in the skill uses Python code, system checks, and timesfm APIs accessible via Python imports. Command references include:
python scripts/check_system.pymodel = timesfm.TimesFM_2p5_200M_torch.from_pretrained("google/timesfm-2.5-200m-pytorch")model.compile(timesfm.ForecastConfig(...))model.forecast(horizon=..., inputs=...)model.forecast_with_covariates(...)for covariates
Caveats
- Model weights are downloaded on-demand from HuggingFace and cached; the repository does not store weights (~800 MB).
- TimesFM 2.5 requires hardware meeting RAM/VRAM constraints as outlined in the preflight checks; insufficient resources block loading.
- Anomaly detection is not built-in; interpretation relies on quantile intervals (prediction intervals) around forecasts.
- For classical multivariate models or clustering, this skill recommends other libraries (statsmodels, aeon).
- License: Apache-2.0 license
# TimesFM Forecasting ## Overview TimesFM (Time Series Foundation Model) is a pretrained decoder-only foundation model developed by Google Research for time-series forecasting. It works **zero-shot** — feed it any univariate time series and it returns point forecasts with calibrated quantile prediction intervals, no training required. This skill wraps TimesFM for safe, agent-friendly local inference. It includes a **mandatory preflight system checker** that verifies RAM, GPU memory, and disk space before the model is ever loaded so the agent never crashes a user's machine. > **Key numbers**: TimesFM 2.5 uses 200M parameters (~800 MB on disk, ~1.5 GB in RAM on > CPU, ~1 GB VRAM on GPU). The archived v1/v2 500M-parameter model needs ~32 GB RAM. > Always run the system checker first. ## When to Use This Skill Use this skill when: - Forecasting **any univariate time series** (sales, demand, sensor, vitals, price, weather) - You need **zero-shot forecasting** without training a custom model - You want **probabilistic forecasts** with calibrated prediction intervals (quantiles) - You have time series of **any length** (the model handles 1–16,384 context points) - You need to **batch-fore
- Overview
- When to Use This Skill
- ⚠️ Mandatory Preflight: System Requirements Check
- Hardware Requirements by Model Version
- 🔧 Installation
- Step 1: Verify System (always first)
- Step 2: Install TimesFM
- Step 3: Install PyTorch for Your Hardware
- Step 4: Verify Installation
- 🎯 Quick Start
- Minimal Example (5 Lines)
- Forecast from CSV
- Forecast with Covariates (XReg)
- Anomaly Detection (via Quantile Intervals)
python scripts/check_system.py Using uv (recommended by this repo) uv pip install timesfm[torch] Or using pip pip install timesfm[torch] For JAX/Flax backend (faster on TPU/GPU) uv pip install timesfm[flax] CUDA 12.1 (NVIDIA GPU) pip install torch>=2.0.0 --index-url https://download.pytorch.org/whl/cu121 CPU only
What does the timesfm-forecasting skill do?
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series mod
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill timesfm-forecasting-foryourhealth111-pix-vibe-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.