Detect anomalies in time series data using Prophet Framework (Meta), which frames the seasonality, trend holiday effect and other needed regressors into its model, to identify unusual surges or slumps in trends. This is a general methodology analyst can use for understanding what changes of their tracking metrics are manifesting anomalies pattern.
Install
npx skills add benchflow-ai/skillsbench --skill time-series-anomaly-detectionnpx skills add benchflow-ai/skillsbench --skill time-series-anomaly-detection -a claude-code -gnpx skills add benchflow-ai/skillsbench --skill time-series-anomaly-detection -a codex -ggemini skills install https://github.com/benchflow-ai/skillsbench.git --path analysis/tasks_skills_low/trend-anomaly-causal-inference/level_2/time_series_anomaly_detectiongh skill install benchflow-ai/skillsbench time-series-anomaly-detectiongit clone --depth 1 https://github.com/benchflow-ai/skillsbench /tmp/benchflow-ai__skillsbench
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/benchflow-ai__skillsbench/analysis/tasks_skills_low/trend-anomaly-causal-inference/level_2/time_series_anomaly_detection ~/.claude/skills/time-series-anomaly-detection # Claude Code
cp -R /tmp/benchflow-ai__skillsbench/analysis/tasks_skills_low/trend-anomaly-causal-inference/level_2/time_series_anomaly_detection ~/.agents/skills/time-series-anomaly-detection # Codex, Cursor, Gemini CLI, Copilot, OpenCode