Does this skill update my local project files?

Yes, after your approval, the skill synchronizes changes to both the internal Basic Memory schema note and your local files located in the schemas/ directory.

How does the frequency analysis work?

The skill analyzes your notes to see how often specific fields are used. It suggests adding fields used in more than 25% of notes and suggests removing fields with 0% usage.

What is schema drift in the context of Claude Code?

Schema drift occurs when the structure of your notes in Basic Memory changes over time—such as adding new fields or stopping use of old ones—causing them to diverge from the original schema definition.

What happens if a schema change causes validation errors?

The skill runs a validation check after every update. If errors occur, it identifies specific notes that need to be fixed to match the new schema definition.

Schema Evolution Manager

Name: Schema Evolution Manager
Author: voxpelli

byvoxpelli

•

Database Management

Maintains knowledge graph integrity by detecting drift between schema definitions and actual note usage in Basic Memory.

The Schema Evolution skill is a specialized tool for maintaining structured knowledge graphs within Claude Code. It identifies 'schema drift' by comparing your formal schema definitions against how you actually use notes in Basic Memory. The skill performs frequency analysis to propose adding emerging fields or removing unused ones, ensuring your data model stays relevant. Once approved, it performs a dual-sync to update both the internal memory notes and your local schema documentation files, providing a seamless workflow for evolving complex data structures without manual editing overhead.

Key Features

01Analyzes field frequency to propose data-driven schema updates

021 GitHub stars

03Synchronizes changes across Basic Memory and local Markdown schema files

04Automates Picoschema generation for new field additions

05Detects schema drift between definitions and actual note usage

06Validates schema integrity and reports note-level inconsistencies

Use Cases

01Identifying and formalizing emerging metadata patterns in a growing knowledge base

02Cleaning up deprecated or unused fields across hundreds of memory notes

03Keeping local technical documentation in sync with live AI memory structures

Key Features

01Analyzes field frequency to propose data-driven schema updates

021 GitHub stars

03Synchronizes changes across Basic Memory and local Markdown schema files

04Automates Picoschema generation for new field additions

05Detects schema drift between definitions and actual note usage

06Validates schema integrity and reports note-level inconsistencies

Use Cases

01Identifying and formalizing emerging metadata patterns in a growing knowledge base

02Cleaning up deprecated or unused fields across hundreds of memory notes

03Keeping local technical documentation in sync with live AI memory structures