Openclaw Setup Guide

Battle-tested setup guide for a multi-agent AI system on Apple Silicon (Mac Mini M4). Covers: install order (Claude Code first), RAM reality for local orches...

This skill appears to honestly document pitfalls and commands for running OpenClaw/Claude Code on Apple Silicon and does not request unrelated credentials or hidden installs. Before running any commands it recommends, do these things: (1) verify the source repository (the README suggests a GitHub clone URL) and inspect any scripts you will execute; (2) create full backups of ~/.openclaw and your workspace as shown (the guide emphasizes this because some commands are destructive); (3) do not run openclaw doctor --repair unless you understand and have backups; (4) be aware that following the guide may require third-party CLIs/APIs (Claude, Kimi, mempalace) which could transmit your config/memory to external services — only use accounts/APIs you trust; (5) if you plan to let an automated agent execute these steps, require explicit human confirmation for any command that reads or writes local config or sends data to the network. If you want, I can review the full SKILL.md sections you plan to run or help identify which external tools referenced will need credentials or further auditing.

Type: OpenClaw Skill Name: nerua1-setup-guide Version: 1.0.0 The bundle is a comprehensive setup and configuration guide for multi-agent AI systems on Apple Silicon. It contains practical advice for managing RAM, preventing configuration overwrites ('lobotomy protection'), and establishing shared memory between agents. All provided shell commands and scripts (e.g., in SKILL.md) are transparent administrative tasks for health checks, backups, and environment management, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.