usage-monitor
Monitor LTX Studio product usage metrics with statistical anomaly detection. Detects data spikes (increases or decreases) in DAU, generations, and token consumption. Use when: (1) daily monitoring and detecting usage anomalies, (2) alerting on segment-specific changes, (3) investigating root causes of engagement shifts.
npx skills add majiayu000/claude-skill-registry --skill usage-lightricks-ltx-analytics-agents --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.
# Usage Monitor ## 1. Overview (Why?) This skill provides **autonomous usage monitoring** using statistical anomaly detection. It compares yesterday's metrics against the last 10 same-day-of-week data points (e.g., last 10 Mondays) and alerts when values deviate by 2 standard deviations from the mean. **Problem solved**: Detect data spikes in usage — both increases and decreases — that indicate significant changes in user behavior, product adoption, feature launches, enterprise churn risk, or engagement shifts. Uses statistical thresholds that adapt to each segment's variance patterns. ## 2. Requirements (What?) Monitor these outcomes autonomously: - [ ] DAU spikes (increases or decreases) by segment (Enterprise Contract/Pilot, Heavy, Paying, Free) - [ ] Image generation volume changes (both increases and decreases) - [ ] Video generation volume changes - [ ] Token consumption trends (spikes up or down) - [ ] Alerts fire when values deviate beyond 2σ (increases or decreases) - [ ] Weekend alerts suppressed for Enterprise (weekday-only monitoring) - [ ] Root cause investigation identifies which orgs/tiers drove changes - [ ] Results formatted with severity (NOTICE vs WARNING vs CRIT
- 1. Overview (Why?)
- 2. Requirements (What?)
- 3. Progress Tracker
- 4. Implementation Plan
- Phase 1: Understand the Statistical Method
- Phase 2: Read Shared Knowledge
- Phase 3: Run Monitoring
- Phase 4: Analyze Results
- Phase 5: Present Findings
- 5. Constraints & Done
- DO NOT
- DO
- Completion Criteria
Install dependency (one-time) pip install google-cloud-bigquery Monitor yesterday (default) python3 usage_monitor.py Monitor specific date python3 usage_monitor.py --date yesterday
What does the usage-monitor skill do?
Monitor LTX Studio product usage metrics with statistical anomaly detection. Detects data spikes (increases or decreases) in DAU, generations, and token consumption. Use when: (1) daily monitoring and detecting usage anomalies, (2) alerting on segment-specific changes, (3) investigating root causes of engagement shifts.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill usage-lightricks-ltx-analytics-agents --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.