remembering-conversations
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
When & Why to Use This Skill
The Remembering Conversations skill acts as a long-term memory layer for Claude Code, enabling users to perform semantic and exact-text searches across archived conversation history. By retrieving historical facts, architectural decisions, and debugging patterns, it ensures project continuity, reduces redundant explanations, and significantly optimizes context window usage during complex development tasks.
Use Cases
- Recalling Architectural Decisions: Quickly find the rationale behind specific design patterns or technical choices discussed in previous sessions to ensure consistency in new implementations.
- Accelerated Debugging: Search for similar error messages or bugs encountered in the past to retrieve proven solutions and troubleshooting steps, preventing the need to solve the same problem twice.
- Technical Fact Retrieval: Locate specific technical details such as Git SHAs, configuration values, or API endpoints that were mentioned or generated in earlier interactions.
- Contextual Continuity: Provide the AI agent with immediate context when a human partner references past discussions ('like we talked about before'), allowing for a seamless transition between different phases of a project.
| name | Remembering Conversations |
|---|---|
| description | Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search |
| when_to_use | when partner mentions past discussions, debugging familiar issues, or seeking historical context about decisions and patterns |
| version | 1.1.0 |
Remembering Conversations
Search archived conversations using semantic similarity or exact text matching.
Core principle: Search before reinventing.
Announce: "I'm searching previous conversations for [topic]."
Setup: See INDEXING.md
When to Use
Search when:
- Your human partner mentions "we discussed this before"
- Debugging similar issues
- Looking for architectural decisions or patterns
- Before implementing something familiar
Don't search when:
- Info in current conversation
- Question about current codebase (use Grep/Read)
In-Session Use
Always use subagents (50-100x context savings). See skills/using-skills for workflow.
Manual/CLI use: Direct search (below) for humans outside Claude Code sessions.
Direct Search (Manual/CLI)
Tool: ${SUPERPOWERS_SKILLS_ROOT}/skills/collaboration/remembering-conversations/tool/search-conversations
Modes:
search-conversations "query" # Vector similarity (default)
search-conversations --text "exact" # Exact string match
search-conversations --both "query" # Both modes
Flags:
--after YYYY-MM-DD # Filter by date
--before YYYY-MM-DD # Filter by date
--limit N # Max results (default: 10)
--help # Full usage
Examples:
# Semantic search
search-conversations "React Router authentication errors"
# Find git SHA
search-conversations --text "a1b2c3d4"
# Time range
search-conversations --after 2025-09-01 "refactoring"
Returns: project, date, conversation summary, matched exchange, similarity %, file path.
For details: Run search-conversations --help