installing-skill-tracker

Installs Claude Code hooks that log skill usage events to JSONL files.

9|2|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/AbdullahMalik17/Hacathan_5 --skill installing-skill-tracker-abdullahmalik17
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: installing-skill-tracker
Source: https://github.com/AbdullahMalik17/Hacathan_5/tree/main/.claude/skills/installing-skill-tracker
Command: npx skills add https://github.com/AbdullahMalik17/Hacathan_5 --skill installing-skill-tracker-abdullahmalik17

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Teams building Claude Code skills have no visibility into which skills are actually used, how often they succeed, or which ones fail. This Skill installs tracking hooks that automatically measure skill usage so you can make data-driven decisions about your skill library. ## Core Features & Use Cases - Automatic Hook Installation: Writes bash hook scripts for UserPromptSubmit, PreToolUse, and PostToolUse events and registers them in .claude/settings.json. - Usage Logging: Captures prompt submissions, skill activations (via SKILL.md reads), and verification results into JSONL activity logs. - Usage Analysis: Generates reports showing invocations, success/failure rates per skill, unused skills, and high-failure-rate skills. - Use Case: After rolling out a set of custom skills to your team, run the analysis script to discover that one procedural skill has a 60% failure rate and three skills are never invoked, then prioritize fixes accordingly. ## Quick Start Set up skill usage tracking in this project by running the setup script and then verifying the installation.

Frequently Asked Questions about installing-skill-tracker

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

FAQPage Schema
How do I track Claude Code skill usage in my project?▼

Run the setup.py script to install tracking hooks into .claude/hooks and register them in .claude/settings.json. The hooks log prompt submissions, skill activations, and verification results to JSONL files under .claude/activity-logs.

How do I measure skill success rates with Claude Code hooks?▼

Run the analyze-skills.py script after some usage. It reads skill-usage.jsonl, separates procedural skills (those with verify.py) from content skills, and reports invocations, success and failure counts, and overall success rates.

Does the skill tracker require jq to be installed?▼

Yes, the bash hook scripts use jq to parse JSON input and write structured JSONL log entries. Install it with brew install jq on macOS or apt install jq on Linux, then re-run verify.py to confirm.

Why does skill tracker verification fail after setup?▼

Verification fails when hook scripts are missing or not executable, jq is unavailable, or settings.json lacks the required UserPromptSubmit, PreToolUse, and PostToolUse hook entries. Re-run setup.py to regenerate missing components.

Will the tracker overwrite my existing Claude Code settings?▼

No. The setup script merges hook entries into the existing settings.json and skips commands already registered, so previously configured hooks and other settings are preserved.