Openclaw Setup Guide
v1.0.0Battle-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...
⭐ 0· 49·0 current·0 all-time
by@nerua1
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (OpenClaw setup on Apple Silicon) matches the SKILL.md content. All instructions, examples, and recommended tools are relevant to installing and operating a multi-agent system on an M4 Mac. There are no unrelated required binaries, environment variables, or install steps declared.
Instruction Scope
The guide instructs the operator to run filesystem-affecting commands (cp backups, restore from backup, edit SOUL.md/AGENTS.md, run openclaw doctor, git log) and to use external CLIs (claude, openclaw, mempalace/capture-idea). That is expected for a setup guide, but these operations touch user config and data; if an automated agent executes them they will read/modify local files and could transmit content to cloud services (e.g., Claude API). The guide explicitly warns about dangerous commands (openclaw doctor --repair) which is helpful. Review and manual confirmation before executing filesystem changes is recommended.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to write to disk. No downloads, package installs, or archive extraction are present in the skill metadata — lowest installer risk.
Credentials
The skill declares no required environment variables or credentials, which aligns with being a pure guide. However, it refers to external services/CLIs (Claude, Kimi/GLM, LM Studio, mempalace/capture-idea) that in practice require credentials or network access; the skill does not request these, so any agent following the guide would need the operator to supply them. Be aware that following the guide may cause data to be sent to third-party APIs if you invoke those services.
Persistence & Privilege
always is false and there is no install step that modifies agent/system-wide settings. The skill does instruct how to modify user config files, but it doesn't claim or request ongoing system presence or escalate privileges. Autonomous invocation is allowed by default on the platform, but that is normal and not a red flag by itself.
Assessment
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.Like a lobster shell, security has layers — review code before you run it.
latestvk9784zkdb1tdf8hge627z6gmhn84p555
License
MIT-0
Free to use, modify, and redistribute. No attribution required.