Does this skill require specific MCP tools?

Yes, it relies on the mcp__ww-memory toolset to access episodic recall, semantic search, spread activation, and procedural skill retrieval.

How does this skill differ from standard RAG?

Unlike basic retrieval-augmented generation, this skill synthesizes information from three distinct memory subsystems and applies advanced filters for recency, relevance, diversity, and actionability.

When should I use the Deep Context format?

Use Deep Context for complex architectural tasks or deep debugging sessions where a chronological timeline, knowledge graph visualization, and pattern analysis are required.

What is World Weaver?

World Weaver is a memory system for Claude that stores episodic history, semantic entities, and procedural skills to improve long-term AI task performance and project awareness.

World Weaver Context Builder

Name: World Weaver Context Builder
Author: astoreyai

byastoreyai

•

Productivity & Workflow

Synthesizes episodic, semantic, and procedural memories into actionable context for AI-assisted development tasks.

About

The World Weaver Context Builder is a specialized Claude Code skill designed to bridge the gap between raw data and actionable project intelligence. By querying the World Weaver memory system, it aggregates recent development history, related entities, and specific procedural skills to provide a structured overview of the current work environment. This skill is particularly effective for developers switching between projects or resuming complex tasks, as it automatically identifies knowledge gaps and highlights previous decisions to ensure continuity and reduce cognitive load during the development lifecycle.

Key Features

1 GitHub stars
Multiple output formats ranging from brief summaries to deep-dive context
Smart filtering based on recency, relevance, and actionability
Automated environmental context gathering via Git and filesystem analysis
Multi-system memory synthesis from episodic, semantic, and procedural stores
Knowledge gap identification to highlight missing project information

Use Cases

Onboarding to a new project or resuming a dormant task with full historical context
Debugging complex issues by retrieving related historical patterns and previous fixes
Synchronizing AI context with recent Git activity and project-specific architectural decisions

About

Key Features

1 GitHub stars
Multiple output formats ranging from brief summaries to deep-dive context
Smart filtering based on recency, relevance, and actionability
Automated environmental context gathering via Git and filesystem analysis
Multi-system memory synthesis from episodic, semantic, and procedural stores
Knowledge gap identification to highlight missing project information

Use Cases

Onboarding to a new project or resuming a dormant task with full historical context
Debugging complex issues by retrieving related historical patterns and previous fixes
Synchronizing AI context with recent Git activity and project-specific architectural decisions