What problem does it solve? LLM responses arrive as unstructured text that breaks downstream code when parsed manually. This Skill uses the Instructor library to force LLM outputs into typed Pydantic models, validating every field and automatically retrying with error feedback when validation fails. ## 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 message is sent back to the LLM and generation retries 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 model, with invalid values automatically corrected through retries. ## Quick Start Use the instructor skill to extract a person's name, age, and email from a block of text into a validated Pydantic model.
