Automates data enrichment, cleanup, and migration pipelines with built-in validation for Supabase databases.
The Data Cleanup Skill empowers Claude to manage complex data operations, from fixing broken media tags to generating story embeddings and validating knowledge bases. It follows a robust workflow involving pre-flight assessments, database snapshots, and self-correcting loops to ensure data integrity during bulk operations. Specifically optimized for Supabase environments, this skill allows for headless automation of data tasks while maintaining strict safety rules, such as sampling changes before execution and requiring explicit user confirmation for any destructive actions.
Key Features
01Headless mode support for unattended bulk data processing
02Automated data enrichment and AI-powered media tagging
03Seamless integration with Supabase for SQL execution and snapshots
04Self-correcting error loops to fix and resume failed pipelines
050 GitHub stars
06Pre-flight database assessment and post-operation validation
Use Cases
01Generating and verifying embeddings for AI-powered search features
02Fixing broken image URLs and validating knowledge base entries
03Cleaning up and reformatting legacy database records and media tags
