anomaly-detector
Detect outliers, spikes, rare events, and abnormal records in tabular or time-series data. Use when the task is anomaly detection or suspicious-pattern review, not generic data-quality linting or full ML pipeline ownership.
npx skills add majiayu000/claude-skill-registry --skill anomaly-detector-foryourhealth111-pix-vibe-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Anomaly Detector ## Purpose Use this skill when the user needs to identify abnormal rows, drift, spikes, or rare-event behavior in data. ## When to Use Use this skill when: - Investigating outlier transactions, sensor spikes, fraud candidates, or rare failures - Comparing statistical, distance-based, or density-based anomaly detection approaches - Setting anomaly thresholds and reviewing false positives or false negatives ## Not For / Boundaries - Generic schema/null/range validation: use `data-quality-checker` - Publication-grade figure polishing: use `scientific-visualization` - End-to-end supervised model training: use `training-machine-learning-models` ## Typical Outputs - Candidate anomaly rules or model choices - Thresholding and review workflow - Follow-up plots or tables showing suspicious records ## Related Skills - `data-quality-checker` for dataset sanity checks before anomaly review - `creating-data-visualizations` for general charts after anomalies are identified
- Purpose
- When to Use
- Not For / Boundaries
- Typical Outputs
- Related Skills
What does the anomaly-detector skill do?
Detect outliers, spikes, rare events, and abnormal records in tabular or time-series data. Use when the task is anomaly detection or suspicious-pattern review, not generic data-quality linting or full ML pipeline ownership.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill anomaly-detector-foryourhealth111-pix-vibe-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.