# analyzing-time-series

analyzing-time-series runs the statistical checks on a CSV time series and tells you whether it is stationary, seasonal or worth differencing before you pick a forecasting model.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1 install · ★ 1438 repo stars
- Author: https-deeplearning-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/https-deeplearning-ai/sc-agent-skills-files/tree/HEAD/L4/custom_skills/analyzing-time-series/SKILL.md
- Updated: 2026-06-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/analyzing-time-series

## What it does

Point it at a CSV time series and it runs the checks you would otherwise do by hand before fitting a forecast. The file needs two columns, one with dates and one with numbers. Names are detected automatically unless you pass `--date-col` and `--value-col`.

Start with `python scripts/diagnose.py data.csv --output-dir results/`. That leaves `diagnostics.json` with the metrics plus `summary.txt` written for a person to read. An optional second pass, `python scripts/visualize.py data.csv --output-dir results/`, writes plots into `results/plots/`: ACF/PACF, a decomposition, rolling statistics, box plots by weekday or month. Run it after the diagnostics, because the plots are synced to the stationarity results.

Interpretation guidance sits in `references/interpretation.md` and covers forecastability, needed differencing and seasonal period. The scripts import `pandas`, `numpy`, `matplotlib`, `statsmodels` and `scipy`, so install those first or nothing runs. `--seasonal-period` overrides the detected period.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add https-deeplearning-ai/sc-agent-skills-files --skill analyzing-time-series -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add https-deeplearning-ai/sc-agent-skills-files --skill analyzing-time-series -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add https-deeplearning-ai/sc-agent-skills-files --skill analyzing-time-series -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install https-deeplearning-ai/sc-agent-skills-files L4/custom_skills/analyzing-time-series
```

2. **Manually: put the files in place**
- File: `.github/skills/analyzing-time-series/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add https-deeplearning-ai/sc-agent-skills-files --skill analyzing-time-series -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/https-deeplearning-ai/sc-agent-skills-files --path L4/custom_skills/analyzing-time-series
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add https-deeplearning-ai/sc-agent-skills-files --skill analyzing-time-series -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/https-deeplearning-ai/sc-agent-skills-files/tree/HEAD/L4/custom_skills/analyzing-time-series/SKILL.md

## When to use it
- Check stationarity before choosing a forecasting model
- Find the seasonal period from the data itself
- Decide how many differences the series needs
- Generate ACF, PACF and decomposition plots in one run
- Tell whether a series is forecastable at all

## Example prompts
- Run the time series diagnostics on `sales.csv` and tell me if it is stationary
- Analyze `data.csv` before I fit a forecast, put the output in `results/`
- Plot ACF and PACF for `temperature.csv` and say what seasonal period it shows

## Similar
- [Time Series Analysis](https://affpapa.org/en/nevibecode/skills/time-series-analysis.md) — skill · 617 installs
- [cloud-monitoring-list-time-series-request](https://affpapa.org/en/nevibecode/skills/cloud-monitoring-list-time-series-request.md) — skill · 4100 installs
- [skforecast-ai](https://affpapa.org/en/nevibecode/mcp/skforecast-ai.md) — MCP server · ★ 52 repo stars
- [aeon](https://affpapa.org/en/nevibecode/skills/aeon.md) — skill · 52 installs
- [statsmodels](https://affpapa.org/en/nevibecode/skills/k-dense-ai-statsmodels.md) — skill · 2400 installs
- [trend-analysis](https://affpapa.org/en/nevibecode/skills/trend-analysis.md) — skill · 8 installs

---
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
