| name | slack-context-memory |
| description | Conversation summarization and context compaction for Slack channels. Reduces context window usage by 70-99% while preserving key information through semantic summaries. |
Slack Context Memory
Compress Slack conversation history into searchable summaries for context-efficient sessions.
Problem Solved
Clawdbot sessions lose context as conversation history grows. This skill:
- Detects conversation boundaries in Slack message history
- Generates structured summaries (TL;DR, decisions, topics, outcome)
- Stores summaries with embeddings for semantic search
- Compacts context - replace 1000s of messages with a few summaries
- Enables semantic retrieval - find relevant past discussions
Quick Start
cd /home/david/clawd/scripts/slack-context-memory
node setup-schema.js
node context-compactor.js C0ABGHA7CBE
node context-compactor.js C0ABGHA7CBE --compare
node context-compactor.js --query "email newsletter filtering"
Token Savings
| Channel | Original | Compacted | Savings |
|---|
| #accounts (1000 msgs) | 112K tokens | 951 tokens | 99.2% |
| #homeassistant (50 msgs) | 3.1K tokens | 911 tokens | 70.8% |
Components
Conversation Detection
node detect-conversations.js <channel_id>
node detect-conversations.js --all
Context Compaction
node context-compactor.js <channel_id> --recent 20
node context-compactor.js <channel_id> --compare
node context-compactor.js --query "search term"
Search
node search-conversations.js semantic "query"
node search-conversations.js text "query"
node search-conversations.js recent --limit 10
Requirements
- PostgreSQL database with pgvector
- Node.js 18+
- Slack message history in database
Database Schema
The conversation_summaries table stores:
tldr - 1-2 sentence summaryfull_summary - Detailed summarykey_decisions - Array of decisions madetopics - Array of topics discussedoutcome - resolved/ongoing/needs-follow-upembedding - Vector for semantic search (1024-dim)
Built for Clawdbot 🦞 | 2026-01-28
