What problem does it solve? LLMs frequently produce malformed JSON, invalid dates, or off-format text that breaks downstream parsing and forces retry loops. This Skill uses Microsoft Research's Guidance framework to enforce output structure at the token level, so generated content always matches the required pattern. ## Core Features & Use Cases - Regex and Grammar Constraints: Guarantee valid emails, dates, phone numbers, JSON objects, and code identifiers by filtering invalid tokens during generation. - Token Healing: Automatically fixes unnatural token boundaries between prompts and generations, eliminating spacing artifacts. - Multi-Step Workflows and Agents: Build ReAct agents, chain-of-thought reasoning, and classification pipelines with Pythonic control flow via the @guidance decorator. - Use Case: Extract structured entities (person, organization, date, location) from unstructured text with guaranteed format compliance, or generate schema-valid JSON for API payloads without post-validation. ## Quick Start Ask the agent to use the guidance skill to generate a JSON user profile with constrained name, age, and email fields using an Anthropic or local model backend.
