A structured memory management skill that compresses conversation history into a high-density Markdown format for efficient context retention.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-compact-summary
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-compact-summary using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Compact Summary: Structured Memory Compression?
Compact Summary is an advanced memory management skill designed to enhance the memory flush and compaction workflows within the OpenClaw ecosystem. By adopting a structured Markdown format for the MEMORY.md file, this skill ensures that essential context, tool usage, and task states are preserved without overwhelming the agent context window. This approach allows for a cleaner transition between long-running sessions while maintaining a high level of technical accuracy and situational awareness for the AI.
Using this skill as part of your Openclaw Skills library enables agents to handle complex, multi-step engineering tasks by distilling hundreds of messages into a single, actionable summary. It focuses on maintaining the technical truth of the workspace while stripping away conversational noise.
Compact Summary: Structured Memory Compression Use Cases
- Managing long-running development sessions where context windows are nearing capacity.
- Triggering a memory flush to clear history while retaining critical project metadata.
- Providing a structured Resume Instruction for agents to continue tasks without conversational overhead.
- Auditing tool usage and file interactions across complex multi-turn workflows.
- Synchronizing state between different agent sessions using a standardized memory format.
How Compact Summary: Structured Memory Compression Works
- The skill identifies a trigger condition, typically during a manual or automatic memory flush or compaction event within the agent environment.
- It analyzes the current conversation scope, calculating message counts for the user, assistant, and specific tool invocations.
- The agent extracts key data points such as primary user requests, pending todo items, and specific files modified or read.
- A structured Markdown summary is generated using standardized headers like Conversation Scope, Key Files, and Timeline.
- The summary is written to the MEMORY.md file in the workspace, providing a compressed but comprehensive state for the next interaction loop.
Compact Summary: Structured Memory Compression Setup
To implement Compact Summary within your Openclaw Skills environment, ensure your agent is configured to recognize the structured memory flush trigger. This skill is a logical workflow and does not require a binary installation.
# Ensure your agent has write access to the workspace root
touch MEMORY.md
# Configure the agent to use the Structured Summary Format
# during any 'memory_flush' or 'compact' operations.
Compact Summary: Structured Memory Compression Data Schema & Taxonomy
The skill organizes memory into a strict hierarchy within the MEMORY.md file to ensure predictable parsing by Openclaw Skills:
| Field | Description |
|---|---|
| Conversation Scope | Metadata including message counts and compression timestamps. |
| Tools Used | A comma-separated list of tools invoked (e.g., exec, grep_search). |
| Todo Items | A Markdown checklist of incomplete tasks and P0 objectives. |
| Key Files | Absolute or relative paths to files relevant to the current task. |
| Timeline | A chronological summary of interactions and tool results. |
| Resume Instruction | A specialized directive to prevent agent repetition after loading memory. |
Compact Summary: Structured Memory Compression Advanced Features
- XML-inspired structured formatting compatible with advanced claw-code summary protocols.
- Automated P0 task tracking to ensure critical path items are never lost during context shifts.
- Detailed tool result logging that captures specific match counts and execution outcomes within the timeline.
- Non-intrusive resume logic that prevents the AI from generating redundant recap text.
- Multi-tool awareness for tracking complex orchestration sequences across Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Aliyun Qwen Omni
A powerful multimodal skill for Alibaba Cloud Model Studio that enables simultaneous image, audio, and text processing.
Aliyun Model Studio Crawl and Skill Generation
A dedicated toolset for synchronizing Alibaba Cloud Model Studio documentation with local AI agent skill definitions.
Aliyun Qwen VL
A professional-grade multimodal skill that enables AI agents to analyze images, read charts, and perform structured visual data extraction using Alibaba Cloud Qwen VL models.
OpenClaw Memory Management Format
A multi-layered memory architecture that combines semantic search with structured Markdown storage to maintain persistent AI agent context.
OpenClaw Hook Examples
A comprehensive guide to intercepting and customizing AI agent behavior using the powerful hook system in Openclaw Skills.
WhatsApp Memory
A persistent, file-based memory system that keeps WhatsApp group and direct message contexts isolated, searchable, and loop-free for AI agents.
Featured*
