memory

Access and use project memories from previous sessions for context-aware assistance.Use when recalling past decisions, checking project conventions, or understanding user preferences.Trigger with phrases like "remember when", "like before", or "what was our decision about".

⭐692stars🔀70forks📁View on GitHub🕐Updated Dec 17, 2025

When & Why to Use This Skill

The Memory skill enables Claude to maintain long-term project context by storing and retrieving key information across multiple sessions. By leveraging a persistent JSON-based storage system, it allows the agent to recall past decisions, adhere to project-specific conventions, and respect user preferences, significantly reducing the need for repetitive instructions and ensuring architectural consistency.

Use Cases

  • 1. Technical Decision Tracking: Recalling the rationale behind specific architectural choices or library selections made in previous sessions to maintain project integrity.
  • 2. Coding Convention Enforcement: Automatically applying project-specific style guides, naming conventions, and documentation patterns stored in the memory file.
  • 3. Workflow Personalization: Remembering user-specific preferences for task prioritization, communication tone, or preferred development tools to provide a tailored experience.
  • 4. Knowledge Persistence: Building a local knowledge base of project 'tribal knowledge' that survives session resets, ensuring the agent remains context-aware over long-term development cycles.
namememory
description|
allowed-toolsRead, Write
version1.0.0
authorJeremy Longshore <jeremy@intentsolutions.io>
licenseMIT

Memory

Overview

This skill provides automated assistance for the described functionality.

Prerequisites

Before using this skill, ensure you have:

  • Project memory file at {baseDir}/.memories/project_memory.json
  • Read permissions for the memory storage location
  • Understanding that memories persist across sessions
  • Knowledge of slash commands for manual memory management

Instructions

  1. Locate memory file using Read tool
  2. Parse JSON structure containing memory entries
  3. Identify relevant memories based on current context
  4. Extract applicable decisions, conventions, or preferences

See {baseDir}/references/implementation.md for detailed implementation guide.

Output

  • Memories applied automatically without announcement
  • Decisions informed by historical context
  • Consistent behavior aligned with past choices
  • Natural incorporation of established patterns
  • List of all stored memories with timestamps
  • Confirmation of newly added memories

Error Handling

See {baseDir}/references/errors.md for comprehensive error handling.

Examples

See {baseDir}/references/examples.md for detailed examples.

Resources

  • /remember [text] - Add new memory to manual_memories array
  • /forget [text] - Remove matching memory from storage
  • /memories - Display all currently stored memories
  • Apply memories silently without announcing to user
  • Current explicit requests always override stored memories