Setup

v1.0.0

Configure OpenClaw installations with optimized settings, channel setup, security hardening, and production recommendations.

⭐ 2· 866·5 current·5 all-time

byIván@ivangdavila

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ivangdavila/setup.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Setup" (ivangdavila/setup) from ClawHub.
Skill page: https://clawhub.ai/ivangdavila/setup
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install setup

ClawHub CLI

Package manager switcher

npx clawhub@latest install setup

Security Scan

VirusTotal

Suspicious

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

The name/description match the content: files contain configuration recommendations for channels, agents, gateway, memory, tools, automation and security. Nothing in the bundle asks for unrelated credentials or binaries, and no hidden functionality is present.

ℹ

Instruction Scope

SKILL.md and the included docs instruct the user to run OpenClaw CLI commands (e.g., `openclaw onboard --install-daemon`, `openclaw doctor`) and to edit config files under ~/.openclaw; those are appropriate for a setup guide. The docs also include placeholders and examples referencing many environment variables/tokens (GATEWAY_TOKEN, TELEGRAM_BOT_TOKEN, OPENAI_API_KEY, etc.). The skill does not itself read or exfiltrate anything, but running the recommended commands or applying suggested settings (daemon install, gateway binding, enabling exec full access) will change system state and can expose services if misconfigured — the docs sometimes recommend insecure options in certain sections (e.g., `exec.security:

Like a lobster shell, security has layers — review code before you run it.

latestvk978gs2vmebks6m1h3wmrj06sd8121sx

866downloads

2stars

1versions

Updated 11h ago

v1.0.0

MIT-0

Quick Reference

Task	Load
Messaging channels (Telegram, WhatsApp, Discord, etc.)	`channels.md`
Agent settings, models, workspaces	`agents.md`
Security, auth, DM policies, allowlists	`security.md`
Tools: exec, browser, web, media	`tools.md`
Cron, hooks, heartbeats, automation	`automation.md`
Recommendations by use case	`recommendations.md`
Memory search, embeddings, QMD	`memory.md`
Gateway: port, TLS, Tailscale, remote	`gateway.md`

First Setup Checklist

Before any config, run:

openclaw onboard --install-daemon  # Full wizard
openclaw doctor                    # Check issues

Minimum viable config:

At least one channel connected (Telegram recommended for testing)
Model configured (Anthropic Claude or OpenAI)
Workspace path set (agents.defaults.workspace)
Owner allowlist configured (your user ID in channels.*.allowFrom)

Config Locations

File	Purpose
`~/.openclaw/openclaw.json`	Main config
`~/.openclaw/.env`	Environment variables
`~/.openclaw/workspace/`	Default workspace
`~/.openclaw/sessions/`	Session storage

Hot reload: Most settings apply instantly. Gateway settings (port, TLS) require restart.

Common Mistakes to Avoid

Open DM policy without allowlist → Anyone can message your bot
No auth token on remote gateway → Exposed to internet
Model without fallbacks → Single point of failure
Heartbeat without delivery target → Lost proactive messages
exec.security: "full" in groups → Dangerous command access

When You're Done

openclaw doctor       # Verify config
openclaw status       # Check runtime
openclaw health       # Gateway health

Comments

Loading comments...