Does this skill allow saving new information?

No, this is a specialized read-only skill. To capture and store new insights, you should use the companion 'memory-save' skill.

What information does it store?

It is designed to track high-level summaries of discussions, technical design patterns, and critical project decisions that help Claude understand the 'why' behind a codebase.

Is it efficient for large knowledge bases?

Absolutely. It uses limit clauses and importance-based ordering to ensure only the most relevant summaries are pulled into the AI's current context.

Can I filter searches by specific criteria?

Yes, the skill allows you to filter by categories, tags, importance levels, and date ranges to pinpoint the exact information you need.

How does Memory Read retrieve information?

It utilizes the Supabase MCP to execute optimized SQL queries against a dedicated 'memories' table, supporting keyword matches, category filters, and vector similarity.

Supabase Memory Read

Name: Supabase Memory Read
Author: iketomo

byiketomo

0•

Gestión de Bases de Datos

Searches and retrieves historical discussions, design decisions, and domain knowledge from a Supabase-backed long-term memory system.

This skill empowers Claude with long-term persistent memory by providing a structured way to query a Supabase 'memories' database. It allows the agent to recall past architectural decisions, technical discussions, and specialized domain knowledge that occurred in previous sessions. By leveraging multiple SQL search patterns—including keyword matching, category filtering, and vector similarity—it ensures that relevant context is always available, maintaining project continuity and preventing the loss of critical insights over time.

Características Principales

01Importance-based ranking to surface critical information first

020 GitHub stars

03Flexible SQL-based searching via Supabase MCP

04Multi-mode retrieval including keyword, category, and tag filtering

05Context-efficient architecture that minimizes token usage

06Support for vector similarity search for semantic context retrieval

Casos de Uso

01Recalling specific architectural decisions from past project phases

02Reviewing historical team discussions to understand legacy code rationale

03Searching for specialized project-specific knowledge and best practices

Características Principales

01Importance-based ranking to surface critical information first

020 GitHub stars

03Flexible SQL-based searching via Supabase MCP

04Multi-mode retrieval including keyword, category, and tag filtering

05Context-efficient architecture that minimizes token usage

06Support for vector similarity search for semantic context retrieval

Casos de Uso

01Recalling specific architectural decisions from past project phases

02Reviewing historical team discussions to understand legacy code rationale

03Searching for specialized project-specific knowledge and best practices