remembering-conversations

Krosebrook's avatarfrom Krosebrook

ALWAYS USE THIS SKILL WHEN STARTING ANY KIND OF WORK, NO MATTER HOW TRIVIAL. You have no memory between sessions and will reinvent solutions or repeat past mistakes UNLESS YOU USE THIS SKILL. Gives you perfect recall of all your past conversations and projects.

⭐1stars🔀1forks📁View on GitHub🕐Updated Dec 30, 2025
[Memory and Context Management]

When & Why to Use This Skill

The Remembering Conversations skill provides Claude with a persistent long-term memory layer, enabling it to search and recall specific insights from all past interactions and projects. By retrieving historical decisions, code patterns, and previous solutions, this skill prevents the AI from reinventing existing logic or repeating past mistakes, ensuring seamless continuity across multiple sessions while optimizing context window usage.

Use Cases

  • Project Continuity: Seamlessly resume complex development tasks by recalling specific architectural decisions and technical constraints established in previous sessions.
  • Efficient Debugging: Rapidly resolve recurring issues by searching for past troubleshooting steps, root cause analyses, and successful fixes.
  • Pattern Consistency: Maintain high standards by ensuring new code implementations or documentation align with established project patterns and style guides found in history.
  • Knowledge Retrieval: Instantly access specific stakeholder requirements, logic explanations, or project milestones from historical data without the need for manual re-uploading.
nameremembering-conversations
descriptionALWAYS USE THIS SKILL WHEN STARTING ANY KIND OF WORK, NO MATTER HOW TRIVIAL. You have no memory between sessions and will reinvent solutions or repeat past mistakes UNLESS YOU USE THIS SKILL. Gives you perfect recall of all your past conversations and projects.

Remembering Conversations

Core principle: Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.

Mandatory: Use the Search Agent

YOU MUST dispatch the search-conversations agent for any historical search.

Announce: "Dispatching search agent to find [topic]."

Then use the Task tool with subagent_type: "search-conversations":

Task tool:
  description: "Search past conversations for [topic]"
  prompt: "Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples]."
  subagent_type: "search-conversations"

The agent will:

  1. Search with the search tool
  2. Read top 2-5 results with the show tool
  3. Synthesize findings (200-1000 words)
  4. Return actionable insights + sources

Saves 50-100x context vs. loading raw conversations.

When to Use

Search proactively:

  • Before implementing features
  • Before making architectural decisions
  • When debugging (especially familiar-seeming issues)
  • When partner mentions past work
  • At the start of ANY non-trivial task

Don't search:

  • For info in current conversation
  • For current codebase structure (use Grep/Read)

Direct Tool Access (Discouraged)

You CAN use MCP tools directly, but DON'T:

  • mcp__plugin_episodic-memory_episodic-memory__search
  • mcp__plugin_episodic-memory_episodic-memory__show

Using these directly wastes your context window. Always dispatch the agent instead.

See MCP-TOOLS.md for complete API reference if needed for advanced usage.