$ loading_
Search past conversations before answering to recover context and avoid wrong assumptions.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "remembering-conversations" skill from askskill: 1. Download https://raw.githubusercontent.com/obra/episodic-memory/main/skills/remembering-conversations/SKILL.md 2. Save it as ~/.claude/skills/remembering-conversations/SKILL.md 3. Reload skills and tell me it's ready
First search our previous conversations about this project, summarize confirmed requirements, open questions, and options I explicitly rejected, then suggest the next steps.
A conversation-based recap of requirements with confirmed items, unresolved points, and recommended next steps.
Before answering this question, search whether we discussed the same topic before, especially my past decisions, constraints, and preferences, then answer based on that context.
An answer grounded in prior conversations that references existing decisions and constraints to reduce repetition.
First search whether we discussed this issue before. If yes, summarize the previous conclusion, any later updates, and where we should continue this time instead of starting over.
A continuity-focused summary of past discussion so the conversation can resume from the latest progress.
Core principle: Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.
YOU MUST search historical memory for any historical search.
Announce: "Searching past conversations for [topic]."
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"
If a search-conversations agent is available, dispatch it with the same prompt. If not, use the MCP tools directly:
search toolread toolThe search workflow will:
search toolread toolSaves 50-100x context vs. loading raw conversations.
Use this whenever the current task would benefit from information you may have learned before, even if the user did not explicitly ask you to search.
When past experience may help:
When you're stuck:
When historical signals are present:
Before answering from uncertainty:
Don't search first:
Use these directly when a search agent is unavailable or the current harness does not support agent dispatch:
mcp__plugin_episodic-memory_episodic-memory__searchmcp__plugin_episodic-memory_episodic-memory__readWhen using MCP tools directly, keep context small: search first, then read only the top 2-5 relevant conversations or line ranges.
See MCP-TOOLS.md for complete API reference if needed for advanced usage.
Clarify intent, requirements, and solution direction before any creative implementation work.
Helps decide merge, PR, or cleanup steps after branch work is complete.
Execute implementation plans by splitting and advancing independent tasks in-session.
Set conversation rules to discover and invoke skills before replying.
Turn requirements into a clear step-by-step execution plan before implementation.
Verify results before claiming work is complete, fixed, or passing.
Search past Claude Code chats to recover facts, decisions, and context.
Give AI agents persistent memory across sessions with automatic context retrieval.
Give AI reliable memory across your documents, notes, and meetings
Turn meetings and voice notes into a searchable, privacy-first AI memory layer.
Maintain cross-session customer context, retrieve memories, and prune stale support facts.
Store and retrieve agent lessons to improve tasks and avoid repeated mistakes.