[BUG] `/insights` skill: AI-generated sections empty (returns {})

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

## Bug Description
Running /insights generates a report where all AI-analyzed sections are empty:

• What You Work On
• How You Use CC
• Impressive Things
• Where Things Go Wrong
• Features to Try
• New Usage Patterns
• On the Horizon

The raw stats sections (Top Tools Used, Languages, file/message counts) populate correctly.

## Root Cause
The insights data passed to the report template is {}. The LLM analysis step runs but returns no structured
output.

## Environment

• Claude Code version: 2.1.156
• OS: macOS Darwin 25.5.0 (arm64)
• Sessions available: 58 session-meta JSON files in ~/.claude/usage-data/session-meta/
• Sessions "analyzed" per report summary: 38

What Should Happen?

## Expected
Each section populated with AI-generated analysis of usage patterns.

## Actual
All sections show "No data". At-a-glance summary shows "_No insights generated_".

Error Messages/Logs

Steps to Reproduce

1. Run /insights (or /insights regenerate)
2. Open the generated HTML report
3. All narrative sections show "No data"

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.156

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_