session-analyzer

Compare Claude Code session executions against SKILL.md specifications.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/karohani/my-claude-friends --skill session-analyzer-karohani
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-analyzer
Source: https://github.com/karohani/my-claude-friends/tree/main/plugins/session-wrap/skills/session-analyzer
Command: npx skills add https://github.com/karohani/my-claude-friends --skill session-analyzer-karohani

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables practitioners to validate Claude Code sessions by comparing actual tool, agent, and hook executions against the expectations outlined in the SKILL.md, helping ensure reliable and predictable behavior.

Core Features & Use Cases

  • Post-hoc session analysis: compare subagent invocations, hooks fired, and artifacts against SKILL.md definitions.
  • Regression and validation: confirm previous session outcomes remain consistent after changes, and verify new skills meet defined criteria.
  • Troubleshooting assistance: surface discrepancies between expected versus actual execution to guide debugging.

Quick Start

Provide a sessionId and targetSkill path to generate a Session Analysis Report that validates behavior against SKILL.md.

Frequently Asked Questions about session-analyzer

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

FAQPage Schema
How do I verify Claude Code session behavior against skill specifications?

Post-hoc session analysis compares actual subagent invocations, hooks fired, and artifacts against SKILL.md definitions to validate skill behavior. Provide a sessionId and targetSkill path to generate a structured Session Analysis Report.

What is post-session analysis for debugging agent execution?

Post-session analysis compares recorded tool, agent, and hook executions against expected SKILL.md definitions to validate reliable and predictable behavior. It surfaces discrepancies between expected versus actual execution to guide debugging.

How do I run a session analysis report for skill regression testing?

To run a session analysis report, provide a sessionId, targetSkill path, and optional validation criteria. The analysis confirms previous session outcomes remain consistent after changes and verifies new skills meet defined criteria.

Do I need jq installed to analyze Claude Code sessions?

Yes, jq is a required dependency to analyze Claude Code sessions. This Skill uses jq to parse session logs and process structured data for generating the validation report.

Can I validate subagent invocations and hooks from a previous session?

Yes, you can validate subagent invocations and hooks from previous sessions. The analysis compares fired hooks and invoked subagents against SKILL.md definitions to confirm expected execution outcomes remain consistent.

Why does my skill execution differ from the SKILL.md specifications?

Skill execution may differ from SKILL.md specifications due to discrepancies in tool, agent, or hook behavior. Running a session analysis surfaces these mismatches between expected and actual execution to guide debugging.