What problem does it solve? LLMs often produce malformed JSON, invalid dates, or off-format text that breaks downstream parsing. This Skill uses the Guidance library to enforce token-level constraints so model outputs always match the required regex, grammar, or selection set. ## Core Features & Use Cases - Regex and Grammar Constraints: Force outputs to match patterns like emails, dates, phone numbers, or full JSON schemas compiled from Pydantic models. - Token Healing: Automatically repairs token boundaries between prompt and generation to avoid spacing artifacts. - Reusable Workflows: Build multi-step reasoning chains, ReAct agents, and data extraction pipelines with the @guidance decorator and Pythonic control flow. - Use Case: Extract structured entities (names, dates, emails) from unstructured text with guaranteed-valid formats, or generate schema-conformant JSON for API payloads without retry loops. ## Quick Start Use the guidance skill to generate a JSON user profile with name, age, and email fields constrained to valid formats using a local Transformers model.
