slack-context-memory

Conversation summarization and context compaction for Slack channels. Reduces context window usage by 70-99% while preserving key information through semantic summaries.

7 stars

Best use case

slack-context-memory is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Conversation summarization and context compaction for Slack channels. Reduces context window usage by 70-99% while preserving key information through semantic summaries.

Teams using slack-context-memory should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/slack-context-memory/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/davidrudduck/slack-context-memory/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/slack-context-memory/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How slack-context-memory Compares

Feature / Agentslack-context-memoryStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Conversation summarization and context compaction for Slack channels. Reduces context window usage by 70-99% while preserving key information through semantic summaries.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 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:

1. **Detects conversation boundaries** in Slack message history
2. **Generates structured summaries** (TL;DR, decisions, topics, outcome)
3. **Stores summaries with embeddings** for semantic search
4. **Compacts context** - replace 1000s of messages with a few summaries
5. **Enables semantic retrieval** - find relevant past discussions

## Quick Start

```bash
# Setup database schema
cd /home/david/clawd/scripts/slack-context-memory
node setup-schema.js

# View compacted context for a channel
node context-compactor.js C0ABGHA7CBE

# Compare original vs compacted size
node context-compactor.js C0ABGHA7CBE --compare

# Search for relevant conversations
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
```bash
node detect-conversations.js <channel_id>
node detect-conversations.js --all
```

### Context Compaction
```bash
node context-compactor.js <channel_id> --recent 20
node context-compactor.js <channel_id> --compare
node context-compactor.js --query "search term"
```

### Search
```bash
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 summary
- `full_summary` - Detailed summary
- `key_decisions` - Array of decisions made
- `topics` - Array of topics discussed
- `outcome` - resolved/ongoing/needs-follow-up
- `embedding` - Vector for semantic search (1024-dim)

---

Built for Clawdbot 🦞 | 2026-01-28

Related Skills

memory-system-v2

7
from Demerzels-lab/elsamultiskillagent

Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.

dory-memory

7
from Demerzels-lab/elsamultiskillagent

File-based memory system for AI agents that forget between sessions.

memory-setup

7
from Demerzels-lab/elsamultiskillagent

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

jpj-memory-manager

7
from Demerzels-lab/elsamultiskillagent

Automatic session logging and memory management for infrastructure, projects, and tools.

smart-context

7
from Demerzels-lab/elsamultiskillagent

Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation.

project-context-sync

7
from Demerzels-lab/elsamultiskillagent

Keep a living project state document updated after each commit, so any agent (or future session) can instantly understand where things stand.

memory-pipeline

7
from Demerzels-lab/elsamultiskillagent

Complete agent memory + performance system. Extracts structured facts, builds knowledge graphs, generates briefings, and enforces execution discipline via pre-game routines, tool policies, result compression, and after-action reviews. Includes external knowledge ingestion (ChatGPT exports, etc.) into searchable memory. Use when working on memory management, briefing generation, knowledge consolidation, external data ingestion, agent consistency, or improving execution quality across sessions.

human-like-memory

7
from Demerzels-lab/elsamultiskillagent

This skill provides long-term memory capabilities for conversations.

enhanced-memory

7
from Demerzels-lab/elsamultiskillagent

Enhanced memory search with hybrid vector+keyword scoring, temporal routing, filepath scoring, adaptive weighting.

persistent-memory

7
from Demerzels-lab/elsamultiskillagent

Three-layer persistent memory system (Markdown + ChromaDB vectors + NetworkX knowledge graph) for long-term agent.

auto-context-manager

7
from Demerzels-lab/elsamultiskillagent

AI-powered automatic project context management.

vta-memory

7
from Demerzels-lab/elsamultiskillagent

Reward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series.