Agent structured output

Skill kjuhwa/skills-hub/skills/agents/agent-structured-output

Configure an agent to return a Pydantic model as its final output instead of plain text.From its SKILL.md

Install

npx -y skills add kjuhwa/skills-hub --skill agent-structured-output

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 281 tokens by cl100k_base, as published. Nobody here has run it

agent-structured-output

Set output_type on an Agent to a Pydantic BaseModel. The SDK enforces structured output and returns a typed instance via result.final_output_as(MyModel).

When to apply

When downstream code must parse the agent's reply (routing, classification, evaluation pipelines). Replaces fragile string parsing with typed data.

Core snippet

from pydantic import BaseModel
from agents import Agent, Runner

class OutlineCheckerOutput(BaseModel):
    good_quality: bool
    is_scifi: bool

outline_checker_agent = Agent(
    name="outline_checker_agent",
    instructions="Read the given story outline, and judge the quality. Also, determine if it is a scifi story.",
    output_type=OutlineCheckerOutput,
)

async def main():
    result = await Runner.run(outline_checker_agent, "A space opera about clones...")
    output = result.final_output_as(OutlineCheckerOutput)
    print(output.good_quality, output.is_scifi)

Key notes

result.final_output is the raw Pydantic model instance when output_type is set
Use result.final_output_as(MyModel) for type-checked access
The agent runs until it produces output matching the schema (strict JSON schema by default)
Works with nested models and optional fields

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.