# timesfm-forecasting

This skill runs zero-shot time-series forecasts with Google TimesFM. Use it for regular-grid CSV data, quantile outputs, XReg covariates, and held-out evaluation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1900 installs · ★ 54652
- Author: K-Dense-AI
- License: LicenseRef-Apache-2.0-license · policy=link-only · description only; the file stays with the author
- Source: https://github.com/K-Dense-AI/scientific-agent-skills/tree/HEAD/skills/timesfm-forecasting/SKILL.md
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/skills/timesfm-forecasting

## What it does

The skill prepares temporal data, checks its regular grid, and runs forecasts with TimesFM. Its default local workflow uses the TimesFM 2.5 checkpoint and can produce quantile forecasts, use XReg covariates, and evaluate predictions on held-out data. The CSV helper is `scripts/forecast_csv.py`; it sorts dates and checks duplicate entries, gaps, and missing values.

Before loading weights, the workflow runs `scripts/check_system.py` and considers RAM, cache space, and batch size. It requires Python 3.10+, `timesfm 3.0.2` with PyTorch, NumPy, and pandas. XReg adds JAX and scikit-learn. Without Python 3.10+, the installation from the skill instructions will not run. TimesFM 3.0 has a separate API, and its downloaded weights are restricted to non-commercial, non-production use.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill timesfm-forecasting -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/timesfm-forecasting/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/timesfm-forecasting/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill timesfm-forecasting -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/timesfm-forecasting/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill timesfm-forecasting -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/timesfm-forecasting/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install K-Dense-AI/scientific-agent-skills timesfm-forecasting
```

2. **Manually: put the files in place**
- File: `.github/skills/timesfm-forecasting/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill timesfm-forecasting -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/K-Dense-AI/scientific-agent-skills --path skills/timesfm-forecasting
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/timesfm-forecasting/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill timesfm-forecasting -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/K-Dense-AI/scientific-agent-skills/tree/HEAD/skills/timesfm-forecasting/SKILL.md

## When to use it
- prepare a CSV on a regular time grid
- forecast sales from historical observations
- generate quantile prediction intervals
- evaluate forecasts on held-out data
- add XReg covariates to a forecast

## Example prompts
- Forecast sales from `monthly_sales.csv` for `horizon` 12 and write the result to `forecasts.csv`.
- Validate this time series, find internal gaps, and prepare it for TimesFM.
- Compare the TimesFM forecast with a naive baseline across rolling forecast origins.

## Similar
- [find-skills](https://affpapa.org/en/nevibecode/skills/find-skills.md) — skill · 4000000 installs
- [frontend-design](https://affpapa.org/en/nevibecode/skills/frontend-design.md) — skill · 1025790 installs
- [grill-me](https://affpapa.org/en/nevibecode/skills/grill-me.md) — skill · 1424476 installs
- [grill-with-docs](https://affpapa.org/en/nevibecode/skills/grill-with-docs.md) — skill · 1219756 installs
- [improve-codebase-architecture](https://affpapa.org/en/nevibecode/skills/improve-codebase-architecture.md) — skill · 1163035 installs
- [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · 678700 installs

From the same set: [k-dense-ai/scientific-agent-skills](https://affpapa.org/en/nevibecode/by/k-dense-ai/scientific-agent-skills.md) — 159 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md