Instructor is a multi-language library for extracting structured, validated data from LLM outputs. It patches LLM client libraries to return Pydantic models (Python) or Zod schemas (TypeScript) instead of raw text, supporting 15+ providers including OpenAI, Anthropic, and Google.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Instructor Structured Data Extraction from LLMs"
slug: "instructor-structured-data-extraction-llms"
description: "Instructor is a multi-language library for extracting structured, validated data from LLM outputs. It patches LLM client libraries to return Pydantic models (Python) or Zod schemas (TypeScript) instead of raw text, supporting 15+ providers including OpenAI, Anthropic, and Google."
github_stars: 12666
verification: "security_reviewed"
source: "https://github.com/567-labs/instructor"
category: "Data Extraction & Transformation"
framework: "Custom Agents"
tool_ecosystem:
github_repo: "567-labs/instructor"
github_stars: 12666
---
# Instructor Structured Data Extraction from LLMs
Instructor is a multi-language library for extracting structured, validated data from LLM outputs. It patches LLM client libraries to return Pydantic models (Python) or Zod schemas (TypeScript) instead of raw text, supporting 15+ providers including OpenAI, Anthropic, and Google.
## Installation
Use the upstream install or setup path that matches your environment:
- pip install instructor
- uv add instructor
Requirements and caveats from upstream:
- python
- [Python](https://python.useinstructor.com) - The original
- [Documentation](https://python.useinstructor.com) - Comprehensive guides
Basic usage or getting-started notes:
- bash
- Or with your package manager:
- poetry add instructor
- Source: https://github.com/567-labs/instructor
- Extracted from upstream docs: https://raw.githubusercontent.com/567-labs/instructor/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/instructor-structured-data-extraction-llms/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.