Skip to content
Get packs

Aeon Time Series ML

Guides an agent through time series classification, forecasting, anomaly detection and more using the aeon toolkit.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
12 files

What it does

Once installed, the agent knows how to work with time-ordered data (sensor readings, prices, measurements over time) using the aeon Python library. It can pick a suitable algorithm for classifying, predicting values, grouping similar series, spotting unusual stretches, finding change points, or searching for similar patterns, and it supplies code examples and notes on which methods are stable versus experimental.

Great for

  • Data scientists building time series classifiers or forecasts in Python
  • Researchers comparing time series algorithms with scikit-learn style code
  • Engineers looking for anomalies or change points in sequential sensor or log data

Skip it if

  • Simple spreadsheet-style trend charts or tasks that standard ML tools already handle, since the skill adds specialised algorithms with more setup
  • Production forecasting or anomaly pipelines relying on the experimental modules (forecasting, anomaly detection, segmentation, similarity search), whose interfaces may change between minor releases
  • Non-Python environments, because the examples and the library target Python 3.11-3.14

Try asking

  • “Classify these sensor recordings into normal and faulty groups using a fast accurate method”
  • “Forecast the next 5 values of this monthly sales series and explain the approach”
  • “Find unusual subsequences in this temperature log using a matrix profile”
  • “Cluster these time series into 3 groups using DTW distance”
Step-by-step guide: how to use Aeon Time Series MLInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 12 original files, the MIT licence and an attribution note.

    aeon.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip aeon.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip aeon.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Pin aeon==1.6.0 as the skill recommends so examples match the reviewed release
  • Prefer stable modules (classification, regression, clustering, distances, transformations) for production work and validate experimental modules carefully
  • Review any installed package and the code the agent runs, since the skill's examples execute Python and may download datasets

What's inside

  • references/anomaly_detection.md
  • references/classification.md
  • references/clustering.md
  • references/datasets_benchmarking.md
  • references/distances.md
  • references/forecasting.md
  • references/networks.md
  • references/regression.md
  • references/segmentation.md
  • references/similarity_search.md
  • references/transformations.md
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.