skills.rest
gujiachun-rainbow
gujiachun-rainbowCOMMUNITY
Explore all skills by this author →
GitHub

Remembering Conversations

Search archived conversations by semantic similarity or exact text matches.

8|1|Updated Apr 15, 2026
Search Tags:#summarization#indexing#cli#embeddings#conversations#semantic-search#remembering
One-click install
npx skills add https://github.com/gujiachun-rainbow/RainClaw --skill remembering-conversations-gujiachun-rainbow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Remembering Conversations
Source: https://github.com/gujiachun-rainbow/RainClaw/tree/main/.trae/skills/remembering-conversations
Command: npx skills add https://github.com/gujiachun-rainbow/RainClaw --skill remembering-conversations-gujiachun-rainbow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic-ai/claude-agent-sdk, @xenova/transformers, better-sqlite3, sqlite-vec.

What problem does it solve?

The Remembering Conversations skill helps teams locate and contextualize past Claude Code discussions by indexing and searching archived conversations, preserving decisions, patterns, and context for faster debugging and knowledge retention.

Core Features & Use Cases

  • Semantic and text search across archived conversations to surface relevant discussions
  • Automatic generation of concise summaries for long conversations to enable quick reviews
  • Quick access to related conversations for debugging, architectural decisions, and pattern discovery

Quick Start

Ask me to search archived conversations for a topic and return summarized results with source pointers.

Frequently Asked Questions about Remembering Conversations

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search past conversations using semantic similarity?▼

The skill searches archived conversations using semantic similarity or exact text matches to retrieve relevant context. It returns a concise synthesis with source pointers while avoiding raw excerpts and preserving context.

Can I use sqlite-vec and better-sqlite3 to index archived CLI conversations?▼

Yes, sqlite-vec and better-sqlite3 are used to index archived CLI conversations locally. This stores embeddings to enable semantic search across historical Claude Code discussions.

What is the best way to retrieve historical architectural decisions from past discussions?▼

The best way to retrieve historical architectural decisions is to apply semantic search across indexed conversations. The skill surfaces relevant discussions and returns concise summaries with source pointers for quick review.

Does this semantic search approach work with Xenova transformers for generating embeddings?▼

Yes, the skill uses @xenova/transformers for generating embeddings. These embeddings power the semantic search functionality to locate and contextualize past conversations accurately.

Are there limitations when retrieving exact text matches from summarized conversations?▼

A limitation is that the skill returns concise syntheses with source pointers while avoiding raw excerpts. This preserves context but means exact verbatim text from the original conversations is not directly returned.

Related Skills

Explore More Data & Analytics Skills→
artsmcartsmc
3

pm-db

Manage projects, specs, jobs, tasks, code reviews, and execution logs in a SQLite database with automated dashboards and memory-bank exports.

Community
Advanced
JohannesKoningsJohannesKonings
9

to-spec

Synthesize active conversation context into structured technical specifications and project requirements.

Community
Intermediate
MSamiulHasnatMSamiulHasnat
1

AgentDB Vector Search

Index embeddings and perform context-aware similarity queries for document retrieval.

Community
Advanced
jurisupportjurisupport
52

clean-legal-db

Query a local SQLite legal database for statutes, regulations, and precedents.

Community
Intermediate