What problem does it solve? Getting reliable, structured data from LLM responses is difficult because raw text outputs are unpredictable and hard to parse. This Skill solves that by enforcing Pydantic schemas on LLM outputs, automatically validating results, and retrying failed extractions with error feedback. ## Core Features & Use Cases - Schema-Validated Extraction: Define Pydantic response models with type hints, field constraints, enums, and nested models so LLM outputs always match your expected structure. - Automatic Retry on Validation Failure: When output fails validation, the error is sent back to the LLM which retries up to a configurable limit. - Streaming Partial Results: Stream partial objects or iterables as the LLM generates them for real-time UI updates. - Multi-Provider Support: Works with Anthropic Claude, OpenAI, and local models via Ollama using a consistent API. - Use Case: Extract company information (name, founded year, industry, employees) from unstructured text paragraphs into a validated CompanyInfo model, or classify articles into fixed categories with confidence scores. ## Quick Start Ask the agent to extract structured fields like name, age, and email from a block of text into a validated Pydantic model using Instructor.
