lookml-content-authoring

Generate and update LookML view, explore, and model files from schema YAML or JSON.

8|Updated Feb 23, 2026

Search Tags:#automation #validation #schema #data modeling #filesystem #lookml

Ready to run

npx skills add https://github.com/rittmananalytics/wire-plugin --skill lookml-content-authoring

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: lookml-content-authoring
Source: https://github.com/rittmananalytics/wire-plugin/tree/main/skills/lookml-content-authoring
Command: npx skills add https://github.com/rittmananalytics/wire-plugin --skill lookml-content-authoring

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually creating and updating LookML files, which can be complex and time-consuming, especially in large or evolving projects.

Core Features & Use Cases

Automated LookML File Generation: Create structured view, explore, and model files based on schema specifications.
Schema Integration: Incorporate user-provided schema YAML or JSON data to produce accurate LookML with correct data types and relationships.
Project Consistency: Ensure adherence to naming conventions and project patterns, facilitating maintainability.
Validation & Error Handling: Check generated LookML for syntax correctness and reference accuracy before deployment.
Use Case: Generate a LookML view for a new customer table, including dimensions and measures, directly from the schema details provided.

Quick Start

Provide schema information and specific table details to begin generating LookML files suitable for your data project.

Frequently Asked Questions about lookml-content-authoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate LookML files from schema definitions automatically?▼

To generate LookML files from schema definitions, provide your schema YAML or JSON data to translate data types and relationships into structured view, explore, and model files suitable for production deployment.

Can I update existing LookML views for evolving data projects without breaking references?▼

You can update existing LookML views by incorporating new schema specifications, ensuring project consistency through adherence to naming conventions and validation checks for syntax and reference accuracy before deployment.

What's the best way to validate LookML syntax before deploying to production?▼

The best way to validate LookML syntax before production deployment is to use automated validation and error handling checks that verify syntax correctness and reference accuracy across your generated view, explore, and model components.

Do I need to provide schema YAML or JSON to create structured LookML components?▼

Yes, you need to provide schema YAML or JSON data as input to accurately produce LookML files, ensuring the generated dimensions and measures correctly reflect the underlying data types and table relationships.

How does schema integration work when translating data types into LookML dimensions and measures?▼

Schema integration works by parsing user-provided schema YAML or JSON specifications, translating the defined data types and table relationships directly into syntactically correct LookML dimensions and measures within structured view files.

Are there limitations when maintaining naming conventions across large LookML projects?▼

When maintaining naming conventions across large LookML projects, limitations arise if user-provided schema specifications deviate from established project patterns, making automated adherence to naming conventions challenging without standardized input formats.