Analyze subagent and skill usage logs to identify adoption patterns and failures.
npx skills add https://github.com/Jonghakseo/my-pi --skill usage-analytics
Please help me install this Agent Skill. Skill: usage-analytics Source: https://github.com/Jonghakseo/my-pi/tree/main/skills/usage-analytics Command: npx skills add https://github.com/Jonghakseo/my-pi --skill usage-analytics
This Skill helps identify usage patterns, failures, underused agents, and inactive skills from activity logs so teams can make evidence-based improvements to their development environment.
Ask the usage-analytics skill to analyze the recent seven days of subagent and skill usage data and summarize the key recommendations.
High-intent search queries and answers about installing and using this skill.
Analyze subagent usage logs by processing the JSONL activity data to identify adoption patterns, failure rates, and execution times. This isolates unreliable agents, detects context overflow, and highlights workflow optimization opportunities for your development environment.
Detect inactive skills by measuring explicit skill invocations and direct reads from the usage analytics JSONL log. This separates invocation metrics from read activity, calculates last-use dates, and flags underutilized skills for configuration improvements.
Review agent performance metrics by filtering the usage analytics JSONL log and registered agent directories by your target period. This separates daily trend metrics, success rates, and execution models to compare usage frequency and pinpoint high-error subagents.
Usage analytics identifies optimization opportunities by processing activity logs to detect context overflow, excessive tool output, and overuse patterns. This yields actionable insights to refine subagent configurations and improve overall workflow efficiency.
Registered agent and skill directories are required alongside the usage analytics JSONL log for accurate time-based trend analysis. These directories enable precise period filtering, metric separation, and valid usage comparisons across your development environment.
High error rates in subagent usage analysis emerge from processing activity logs that track failure rates, execution times, and context overflow. Identifying these patterns reveals unreliable agents and pinpoints concrete configuration or workflow improvements needed.
paulnsorensenAggregate Claude Code JSONL session logs into a queryable DuckDB database.
stephanesoaresDefine activation metrics and design guided onboarding flows to reduce drop-offs.
BagelHoleConfigure Azure Monitor diagnostic settings to export activity logs to Log Analytics.
flonatAnalyze JSONL skill invocation logs to report performance metrics and trends.
