structured-output

Convert LlmAgent model responses into validated Pydantic objects using output_schema.

19|6|Updated Mar 12, 2026

Search Tags:#pydantic #streaming #schema validation #structured output #llm agent #json parsing

Ready to run

npx skills add https://github.com/NicolaiLassen/orxhestra --skill structured-output-nicolailassen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: structured-output
Source: https://github.com/NicolaiLassen/orxhestra/tree/main/docs/skills/structured-output
Command: npx skills add https://github.com/NicolaiLassen/orxhestra --skill structured-output-nicolailassen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured-output helps you stop unreliable free-form responses by forcing LLM agents to return validated, typed Pydantic objects you can safely consume in your code.

Core Features & Use Cases

Typed responses with Pydantic: Provide an output_schema so the agent returns a validated model instance instead of text.
JSON extraction + validation: The system appends format instructions, parses JSON, and validates against your schema.
Streaming-friendly parsing: Works with astream() so you can inspect the final typed object once the response completes.

Quick Start

Use structured-output to configure your LlmAgent with an output_schema like CompanyAnalysis and then parse the final event to read analysis.recommendation and analysis.confidence.

Frequently Asked Questions about structured-output

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I get reliable JSON parsing from an LLM agent?▼

To get reliable JSON parsing from an LLM agent, you provide an output_schema so the agent returns a validated Pydantic object instead of free-form text. The system appends parser format instructions, extracts JSON, and validates it against your schema.

What is the best way to enforce schema validation on streaming LLM responses?▼

Schema validation on streaming responses works with astream() to inspect the final typed object once the response completes. You supply a Pydantic output_schema, and the parser extracts and validates the JSON chunks as they arrive.

How do I use Pydantic to extract structured data from multi-agent workflows?▼

To use Pydantic to extract structured data from multi-agent workflows, configure your LlmAgent with a defined output_schema. This enforces consistent structured data extraction across multi-agent compositions by validating model responses into typed objects.

Does structured output work with agents that occasionally return malformed JSON?▼

Structured output handles malformed JSON by providing a fallback structured parsing path. If standard JSON extraction fails, the fallback path attempts to recover and validate the response against your Pydantic schema.