Skills
.Work. You
Rest

ai-core/structured-outputs

Official

Get typed JSON from LLM chat sessions

Software Engineering#schema#llm#zod#chat#structured-output#typed-responses
AuthorTanStack
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LLM chat responses need deterministic, type-safe payloads but providers expose different knobs, so this skill forces chat() to emit validated JSON objects without dealing with provider-specific response formats.

Core Features & Use Cases

  • Provider-agnostic schema handling: the adapter translates outputSchema declarations into each provider's response format, keeping structured output configuration centralized.
  • Multi-library schema support: Zod, ArkType, and Valibot schemas work out of the box, with convertSchemaToJsonSchema() available for manual conversions when needed.
  • Use case: extract person or company data from conversation transcripts and immediately consume the typed result for reporting or downstream logic.

Quick Start

Ask the ai-core/structured-outputs skill to parse a chat message with a Zod schema and return the validated object.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ai-core/structured-outputs
Download link: https://github.com/TanStack/ai/archive/main.zip#ai-core-structured-outputs

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.