Loading...
Loading...
Found 513 Skills
Use when self-hosting OpenClaw on a Linux VPS or cloud server, hardening a remote OpenClaw gateway, choosing between SSH tunneling, Tailscale, or reverse-proxy exposure, or reviewing Podman, pairing, sandboxing, token auth, and tool-permission defaults for a secure personal deployment.
Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Comprehensive security auditor for OpenClaw skills. Checks for typosquatting, dangerous permissions, prompt injection, supply chain risks, and data exfiltration patterns — before you install anything.
Configure Moltbot/OpenClaw for CloudBase full-stack development. Checks ~/.openclaw/ or ~/.clawdbot/ config, finds workspace directory, updates AGENTS.md, and configures mcporter with CloudBase MCP. Guides users to get environment ID and API keys.
Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network, and process access.
Audit your OpenClaw environment for credential leaks, unsafe defaults, and missing sandbox configuration. Wizard-style: answers questions about your setup and produces a fix checklist.
Audit npm, pip, and Go dependencies that OpenClaw skills try to install. Checks for known vulnerabilities, typosquatting, and malicious packages.
Analyze OpenClaw skill permissions and explain exactly what each permission allows. Identifies over-privileged skills and suggests minimal permission sets.
4-tier autonomous self-healing system for OpenClaw Gateway with persistent learning, reasoning logs, and multi-channel alerts. Features Claude Code as Level 3 emergency doctor for AI-powered diagnosis and repair.
Forge a complete lobster soul solution for OpenClaw AI Agent. Based on user preferences or random gacha, output identity positioning, soul description (SOUL.md), role-based bottom-line rules, name, and avatar generation prompts. If the current environment provides an audited image generation skill, it can automatically generate avatar images with unified style. Use this when users need to create, design or customize OpenClaw lobster souls. Not applicable for: fine-tuning existing SOUL.md, character design for non-OpenClaw platforms, pure tool-type Agent without personality. Trigger words: 龙虾灵魂, 虾魂, OpenClaw 灵魂, 养虾灵魂, 龙虾角色, 龙虾定位, 龙虾剧本杀角色, 龙虾游戏角色, 龙虾 NPC, 龙虾性格, 龙虾背景故事, lobster soul, lobster character, 抽卡, 随机龙虾, 龙虾 SOUL, gacha.
Manage OpenClaw bot configuration - channels, agents, security, and autopilot settings
Sanitize OpenClaw agent output before display. Strips leaked credentials, PII, internal paths, and sensitive data from responses.