skill-stats

Analyzes Claude Code transcript JSONL files to extract per-skill usage statistics including invocations, triggers, and hits across projects and time ranges.

Updated Jan 30, 2026
One-click install
npx skills add https://github.com/takemi-ohama/ai-plugins --skill skill-stats
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-stats
Source: https://github.com/takemi-ohama/ai-plugins/tree/main/plugins/ndf/skills/skill-stats
Command: npx skills add https://github.com/takemi-ohama/ai-plugins --skill skill-stats

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps teams understand how often and where NDF Skills are used by analyzing Claude Code transcripts, exposing gaps and opportunities for improvement.

Core Features & Use Cases

  • Analyze transcript JSONL files to count invocations, triggers, and hits per skill.
  • Aggregate usage by project and time window to reveal trends and underutilized skills.
  • Identify new skill candidates by analyzing gaps between triggers and actual invocations to guide improvements.

Quick Start

Run /ndf:skill-stats to generate usage statistics for NDF skills from your transcripts.

Frequently Asked Questions about skill-stats

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track Claude Code skill usage statistics from transcript files?

NDF skill usage statistics are generated by scanning transcript JSONL files to count invocations, triggers, and hits per skill. This process reveals exactly how often and where each skill is used across your projects.

What are skill usage statistics and how do they help optimize my projects?

Skill usage statistics quantify how often specific skills are invoked within Claude Code. By analyzing these metrics, you can identify which triggers are effective, spot underutilized skills, and find gaps in your skill coverage to guide improvements.

Can I aggregate Claude Code skill invocations by project and time range?

Yes, you can aggregate skill invocations by project and time window. Analyzing the transcript JSONL data across these dimensions reveals usage trends and highlights which skills are underutilized within specific project contexts.

How do I identify gaps in skill coverage to find new skill candidates?

To identify gaps in skill coverage, you analyze the discrepancies between skill triggers and actual invocations within your transcripts. Finding these gaps highlights areas lacking effective tools and guides new skill candidate development.

Do I need any specific dependencies to analyze Claude Code transcripts?

You do not need specific dependencies to analyze Claude Code transcripts. The skill operates independently by directly scanning your local transcript JSONL files to produce per-skill usage metrics for reporting.