# Analyze Insights

> Analyze Claude Code /insight report and generate actionable files

- **Type:** Skill
- **Install:** `agentstack add skill-yahav10-claude-insights-analyze-insights`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [yahav10](https://agentstack.voostack.com/s/yahav10)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [yahav10](https://github.com/yahav10)
- **Source:** https://github.com/yahav10/claude-insights/tree/main/skills/analyze-insights

## Install

```sh
agentstack add skill-yahav10-claude-insights-analyze-insights
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## When to Use This Skill

- When you have a Claude Code /insight report HTML file to analyze
- After running `/insight` in Claude Code and saving the HTML report
- When you want to generate skills, CLAUDE.md rules, hooks, and todos from your usage patterns

## Steps

1. **Locate the report**: Find the /insight HTML report file. Common locations:
   - `~/.claude/usage-data/report.html`
   - A saved file from the browser after running `/insight`

2. **Run the analysis**: Execute claude-insights (auto-detects the report, or pass a path):
   ```bash
   npx claude-insights analyze -o ./insights
   npx claude-insights analyze  -o ./insights
   ```

3. **Review the output**: Check the generated files in the output directory:
   - `insights-todo.md` — Prioritized task list
   - `CLAUDE.md-additions.md` — Rules to add to your CLAUDE.md
   - `.claude/settings-insights.json` — Hook configurations
   - `.claude/skills/*/SKILL.md` — Generated skills
   - `insights-README.md` — Placement guide

4. **Apply directly** (alternative): Use `--apply` to merge directly into your project:
   ```bash
   npx claude-insights analyze --apply
   ```

5. **Verify**: Check that the generated rules and skills make sense for your project.

## Rules

- Always review generated output before applying to your project
- The `--apply` mode deduplicates rules — safe to run multiple times
- Generated skills are based on YOUR friction patterns and are project-specific

## Examples

```bash
# Auto-detect report and apply (simplest)
npx claude-insights analyze --apply

# Wait for report to appear, then apply
npx claude-insights analyze --wait --apply

# Standard analysis with explicit file
npx claude-insights analyze ~/report.html -o ./my-project

# With facet data enrichment
npx claude-insights analyze --apply --facets

# Watch for report changes
npx claude-insights watch ~/report.html -o ./my-project

# Team aggregation
npx claude-insights team report1.html report2.html -o ./team-output
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [yahav10](https://github.com/yahav10)
- **Source:** [yahav10/claude-insights](https://github.com/yahav10/claude-insights)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-yahav10-claude-insights-analyze-insights
- Seller: https://agentstack.voostack.com/s/yahav10
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.