# Reliable LLM structured output (/ai--structured-output)

/ai--structured-output is a Claude Code skill in the AI & Agents section. Makes a model return dependable JSON or typed objects: schema design, native structured modes, validation and bounded repair loops.

- Web version: https://skills.sgomez.dev/en/s/ai--structured-output
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ai/structured-output.md
- Updated 10 Jul 2026

## How to ask for it

- `/ai--structured-output make the model always return valid JSON`
- `/ai--structured-output define a schema to extract data from invoices`
- `/ai--structured-output add a repair loop for output that fails schema validation`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ai-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*`
- Writes: `**/*`
- Runs: `project test runners`
- Network: No
- Destructive: No

## Author's description

Reliable structured output - schemas, native modes, validation, repair loops

- [How we review this](https://skills.sgomez.dev/en/methodology.md)