skills.rest
will-flemmer
will-flemmerCOMMUNITY
Explore all skills by this author →
GitHub

Persistent Context Management

Store and retrieve structured knowledge across Claude Code development sessions.

Updated Aug 23, 2026
Search Tags:#context#knowledge management#AI agent#MCP#learning#memory#persistent storage
One-click install
npx skills add https://github.com/will-flemmer/claude-config --skill persistent-context-management
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Persistent Context Management
Source: https://github.com/will-flemmer/claude-config/tree/main/skills/memory/persistent-context
Command: npx skills add https://github.com/will-flemmer/claude-config --skill persistent-context-management

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill establishes a long-term memory system for Claude Code, allowing agents to learn from past decisions, avoid repeated mistakes, and leverage proven patterns across development sessions, preventing knowledge loss and accelerating future tasks.

Core Features & Use Cases

  • Structured Knowledge Storage: Stores architectural decisions, code patterns, bug fixes, performance optimizations, failed approaches, and tool evaluations in a structured format.
  • Intelligent Context Retrieval: Queries memory for relevant past context before planning, enriching task understanding and guiding decision-making.
  • Workflow Integration: Seamlessly integrates memory querying into plan-task and knowledge storage into implement-plan workflows for continuous learning.
  • Relationship Mapping: Allows creation of relationships between stored entities, building a rich, interconnected knowledge graph.
  • Use Case: Before starting a new feature, you can query the memory for similar past tasks, architectural constraints, and failed approaches, ensuring you build upon collective wisdom and avoid repeating past mistakes.

Quick Start

Before planning a new task, use search_nodes to query memory for similar past tasks, architectural decisions, and failed approaches. Include these findings in your task context. After completing a task, use create_entities to store new architectural decisions, code patterns, bug fixes, and lessons learned, linking them with create_relations.