Devboxes

Trust Score 68/100

from ProSkills: OpenClaw community skills10

Manage OpenClaw devbox containers with VSCode Web, noVNC, and automated routing (Traefik or Cloudflare Tunnel); includes onboarding and operational checks.

triggers:devboxspawn devboxopenclaw devboxsetup devboxdev environment

GitHub SKILL.md

What it does

Operational skill for managing OpenClaw devbox sandboxes: onboarding, docker checks, routing setup (Traefik/Cloudflare), ID assignment, env var construction, spawning subagents, and lifecycle management.

When to use it

Use when setting up or managing per-session devboxes, validating Docker/routing prerequisites, or onboarding infrastructure for dev environments.

What's included

Scripts: none declared, but the repo includes a references/setup-script-guide.md for conventions.
References: detailed procedural steps and config examples present in the SKILL.md.
Instructions: onboarding flow, config snippets, spawn/cleanup workflow, and env var references.

Compatible agents

Agents with exec and docker access (main OpenClaw agent, CLI-capable assistants).

Audit Summary

Devbox skill for managing OpenClaw sandbox containers with VSCode Web, noVNC, and routing via Traefik or Cloudflare Tunnels. No bundled scripts — all logic is declarative instructions in SKILL.md. The onboarding flow is thorough but includes risky permission changes (chmod 666 on Docker socket, chmod 777 on host paths) and passes secrets as container env vars. Well-structured documentation with clear two-phase startup and environment variable tables.

Watch Out

Requires Docker socket access and specific Docker bind mounts
Onboarding requires chmod 666 on Docker socket — security risk on shared hosts
Traefik routing requires chmod 777 on host traefik path due to OpenClaw security restrictions
Command templates in openclaw.json config section contain inline comments that would break if copied literally

Notes

Legitimate OpenClaw devbox management skill. Security deductions mainly from recommended permission relaxations (chmod 666/777) and secrets-as-env-vars pattern. These are somewhat inherent to the Docker-in-Docker approach and not malicious. No scripts to test.

Information

Repository: ProSkills: OpenClaw community skills
Stars: 10
Installs: 0

Trust Score

Overall68

Security70

Code Quality68

Architecture65

Usefulness45

Related Skills

AWP (Agent Work Protocol)

Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r

Sync Production Database to Development

Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).

Sandbox0 Integration

Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.

Unitree Robot Controller

Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.

Cursor Hello World Tutorial

A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.

Sendly SMS — Sending SMS

Send transactional or marketing SMS using the Sendly API or Node SDK; supports single, batch, scheduled sends, sandbox testing, and conversation threading.

Easy OpenClaw Config Guide

Interactive configuration and optimization guide for OpenClaw—walks users through testing, three rounds of channel-specific tuning, and optional channel onboard

Claw Release

Release automation for OpenClaw skills: version bumping, tagging, packaging, and CI verification for skill releases.

Back to Skills