What problem does it solve? LLM responses arrive as unstructured text that breaks downstream code when parsed manually. This Skill teaches how to use the Instructor library to force LLM outputs into typed Pydantic models, with automatic validation and retries when the model returns malformed data. ## Core Features & Use Cases - Schema-Validated Extraction: Define Pydantic response models with field constraints, enums, and custom validators so LLM outputs always match your expected structure. - Automatic Retry on Validation Failure: When output fails validation, the error is fed back to the LLM and retried up to a configurable limit. - Streaming and Multi-Provider Support: Stream partial objects or iterables in real time, and switch between Anthropic, OpenAI, and local Ollama models with a consistent API. - Use Case: Extract company name, founding year, industry, and employee count from a paragraph of text into a typed CompanyInfo object, with automatic retries if any field fails validation. ## Quick Start Ask the agent to extract structured fields from a block of text into a Pydantic model using Instructor with your configured LLM provider.
