# Summarize

> Produce a structured review summary. Call this when you have completed your review.

- Skill: `counterpointconsulting/summarize-5` (Agent Skill)
- Install (CLI): `npx skillmds@latest add counterpointconsulting/summarize-5`
- Raw SKILL.md: https://api.skillmd.com/api/skills/counterpointconsulting/summarize-5/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: CounterpointConsulting (https://skillmd.com/u/counterpointconsulting)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/counterpointconsulting/summarize-5

---


# Summarize Your Review

Write a JSON file at /output/result.json:

```json
{
  "status": "approved | changes_requested | concerns",
  "summary": "Brief overall assessment",
  "approved": true,
  "findings": [
    {
      "severity": "critical | warning | info | suggestion",
      "file": "path/to/file",
      "description": "What was found",
      "suggestion": "How to fix it"
    }
  ]
}
```

Set "approved" to false if there are any critical or warning findings.
Set "approved" to true only if all findings are info or suggestion level.

IMPORTANT: Write the file using the write tool to /output/result.json.