What problem does it solve? LLMs frequently produce malformed JSON, invalid formats, or off-spec outputs that break downstream parsing and require costly retry loops. This Skill uses Microsoft Research's Guidance framework to constrain generation at the token level so outputs always match the required structure. ## Core Features & Use Cases - Regex and Grammar Constraints: Enforce formats like emails, dates, phone numbers, JSON, XML, and CSV directly during token generation. - Token Healing: Automatically repairs token boundaries between prompts and generations to avoid spacing artifacts. - Multi-Step Workflows and Agents: Build ReAct agents, chain-of-thought pipelines, and classification systems with Pythonic control flow via the @guidance decorator. - Use Case: You need an API that always returns valid JSON user profiles. Define regex constraints for each field, and Guidance guarantees the model output parses cleanly on the first attempt. ## Quick Start Use the guidance skill to generate a JSON object with name, age, and email fields where each value is constrained by a regex pattern.
