metaclawGenerischer Skill für Memory-Management, Hybrid Retrieval und Skill Evolution mit PluginEval Integration
Install via ClawdBot CLI:
clawdbot install donmeusi/metaclawGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://img.shields.io/badge/Quality-Gold-blue.svgAI Analysis
The skill primarily performs local memory management operations (vector search, extraction, session counting) and does not appear to send user data to external servers. The only external call is to a static badge image (img.shields.io) for documentation display, which poses minimal risk. No credential harvesting, intent override, or obfuscation patterns were detected.
Audited Apr 16, 2026 · audit v1.0
Generated May 6, 2026
A large company uses MetaClaw's hybrid retrieval (semantic + keyword) to enable employees to quickly find relevant documents, meeting notes, and project updates across thousands of files, improving productivity and decision-making. Automatic memory extraction from daily sessions keeps the knowledge base current without manual effort.
A customer support team deploys MetaClaw to automatically extract and consolidate interaction histories from support sessions. Hybrid retrieval allows agents to instantly access past resolutions and customer preferences, reducing response time and increasing satisfaction.
Researchers use MetaClaw to manage personal notes, literature references, and experiment logs. The skill consolidates memories every N sessions, ensuring that key findings and insights are preserved and easily searchable via semantic or keyword queries.
A development team integrates MetaClaw into their workflow to track project state, preferences, and technical decisions across sprints. Hybrid retrieval helps developers quickly recall past discussions and code context, while session counter triggers automatic consolidation to prevent information overload.
An individual uses MetaClaw to automatically extract and organize daily activities, notes, and to-dos from their sessions. Hybrid search enables easy retrieval of past events or ideas, and automatic consolidation keeps the memory file concise and relevant.
Offer a free tier with basic retrieval and limited memory extraction, and a premium subscription for advanced features like custom consolidation intervals, higher query limits, and priority support.
Sell licenses to companies for on-premises deployment, including integration support, custom configuration, and compliance with data residency requirements. Revenue from upfront license fees and annual maintenance.
Provide the core skill as open source to build community and adoption, while offering a fully managed cloud service with auto-scaling, backup, and dedicated support for a monthly fee.
💬 Integration Tip
Start by setting up the Python virtual environment and configuring the memory/config.yaml with your desired retrieval mode and consolidation interval, then integrate the session counter into your heartbeat script.
Scored May 6, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Automatically prune and compact agent memory files to prevent unbounded growth. Circular buffer for logs, importance-based retention for state, and configura...
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refre...
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder rera...