AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

aeon Time Series Machine Learning

A skill that guides Claude through the scikit-learn-compatible aeon toolkit for time series classification, regression, clustering, forecasting and anomaly detection.

Data & AnalyticsIntermediate★ 56,496⑂ 4,969AI score 9/10Last updated: Nov 2, 2026

What it does

Teaches Claude to use the Python aeon toolkit (pinned to 1.6.0) correctly whenever you work with time-indexed data.

  • Ready-to-run patterns for classification (ROCKET, HIVE-COTE, InceptionTime), regression and clustering (DTW K-Means)
  • Forecasting (Naive, ARIMA with iterative_forecast), anomaly detection (STOMP), change-point segmentation (ClaSP), subsequence search (MASS)
  • ROCKET/Catch22 feature extraction, normalization, imputation, elastic distance measures and deep-learning architectures
  • Best practices: (n_cases, n_channels, n_timepoints) data layout, leakage-free validation splits, baseline comparisons
  • Eleven references/*.md catalogs for deeper algorithm choices

Who it's for

  • Data scientists and researchers working with sensor, log, financial or biomedical signals
  • scikit-learn users who are unsure which time-series-specific algorithm to pick
  • Anyone who needs a reproducible, version-pinned time series experiment pipeline for a report or paper

Examples

  1. "Find anomalous windows in this factory sensor log" → STOMP matrix profile scores with a 95th-percentile threshold
  2. "Build a classification baseline for multivariate ECG data" → Normalizer + MiniRocketClassifier pipeline benchmarked against 1-NN Euclidean
  3. "Forecast the next 5 months of revenue" → ARIMA(p,d,q) via iterative_forecast(prediction_horizon=5)

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/aeon/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/aeon folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/aeon/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/aeon ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS, WSL or Git Bash on Windows).
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/aeon ~/.claude/skills/
  5. Install the library: uv pip install "aeon==1.6.0" (add stumpy for matrix-profile examples, TensorFlow for deep learning estimators).
  6. Confirm your interpreter is Python 3.11–3.14: python --version
  7. Restart Claude Code and ask something like "detect anomalies in this time series" — the skill will load automatically.
View source on GitHub ↗License: MIT