Dt Obs Predictive Analytics

This adds forecasting and anomaly detection to Dynatrace observability using DQL and the built-in analyzer tools. You get capacity planning with timeseries-forecast, trend onset detection with timeseries-novelty-detection, and anomaly flagging with adaptive and seasonal detectors. The documentation makes a sharp distinction worth understanding: novelty detection answers "did this metric change" while anomaly detectors answer "is this currently wrong." The skill pushes you toward the forecast analyzer for real predictions and away from naive linear extrapolation. Results come formatted as ranked tables with trend indicators and action flags. If you're trying to answer "which hosts hit 90% CPU in 30 days" or "when did memory usage start climbing," this gives you the query patterns and tool routing you need.

skills.sh installs: 2.4K
GitHub stars: 177
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dynatrace/dynatrace-for-ai --skill dt-obs-predictive-analytics --agent claude-code

Installs into .claude/skills of the current project.

Files

Predictive Analytics Skill

Forecast resource saturation, detect trends, analyze anomalies, and characterize signal behavior using DQL and Dynatrace analyzer tools.

Analysis Disciplines

#	Discipline	Use when …
1	Forecast and Prediction	Predicting future metric values for capacity planning, cost estimation, or proactive alerting
2	Detecting Changes	A metric shifted — find when the character of the signal changed, regardless of whether it crossed a limit
3	Detecting Violations	A metric is currently out of bounds — find entities that exceed or fall below an acceptable range
4	Timeseries Characteristics	Characterizing a signal's seasonality, noise level, and trend before further analysis