How does Forgetful decide what information to save?

The skill uses an importance scoring system (1-10) and an atomicity test to ensure only high-value, distinct concepts like architectural decisions or complex solutions are preserved.

How does the skill handle long-form documentation?

For content exceeding 2000 characters, the skill creates a primary document and extracts 3-5 atomic memories as entry points that link back to the full content.

What is the Zettelkasten method in this context?

It refers to storing knowledge as 'atomic' notes—short, single-concept entries that are easily searchable and interlinked to form a semantic knowledge graph.

Can I use Forgetful across different git repositories?

Yes, the skill includes tools to discover and list projects based on their git remote URLs, allowing for repository-specific memory scoping.

What happens if I try to create a duplicate memory?

The 'Query Before Create' principle encourages checking for existing entries; if a similar memory exists, the skill recommends updating or linking instead of duplicating.

Forgetful Semantic Memory

Name: Forgetful Semantic Memory
Author: ScottRBK

byScottRBK

•

Productividad y Flujo de Trabajo

Implements a structured, Zettelkasten-based semantic memory system to store and retrieve long-term project context, decisions, and patterns.

Acerca de

Forgetful is a specialized skill that empowers Claude with a persistent knowledge base using atomic note principles. It provides a rigorous framework for deciding when to record information versus when to query existing records, ensuring that architectural decisions, technical patterns, and user preferences are preserved across sessions. By utilizing importance scoring, semantic clustering, and project discovery based on Git metadata, it helps maintain a manageable and highly relevant knowledge graph that prevents duplicate entries and surface-level noise.

Características Principales

Git-based project discovery and repository scoping
Bi-directional linking between memories, entities, and documents
Zettelkasten-based atomic memory structuring
Automated semantic querying and relevance ranking
2 GitHub stars
Importance scoring system for long-term retention

Casos de Uso

Documenting architectural decisions and the rationale behind them for future reference
Retrieving project-specific coding patterns and solutions during new feature development
Maintaining a persistent knowledge base of developer preferences and workflow configurations

Acerca de

Características Principales

Git-based project discovery and repository scoping
Bi-directional linking between memories, entities, and documents
Zettelkasten-based atomic memory structuring
Automated semantic querying and relevance ranking
2 GitHub stars
Importance scoring system for long-term retention

Casos de Uso

Documenting architectural decisions and the rationale behind them for future reference
Retrieving project-specific coding patterns and solutions during new feature development
Maintaining a persistent knowledge base of developer preferences and workflow configurations