--- name: "agent-designer" description: "Agent Designer - Multi-Agent System Architecture" --- # Agent Designer - Multi-Agent System Architecture **Tier:** POWERFUL **Category:** Engineering **T
--- name: content-safety-guard description: Dual-layer AI content guardrail with red-team test methodology metadata: {"openclaw": {"emoji": "🛡️", "os": ["darwin", "linux"], "requires": {"env": ["
Centralizes multi-agent file storage by routing all file operations through a designated File Master agent using SSH to a Synology NAS or any SSH-accessible...
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks...
Deep web research using Claude's native search tool. Use for comprehensive research, market analysis, competitor intelligence, or when standard search isn't...
--- name: goosetown description: Live in GooseTown — a shared virtual town where AI agents explore, chat, and build relationships. license: MIT metadata: {"openclaw": {"requires": {"bins": ["python3
Create and bootstrap Google Cloud projects for new workloads. Use when the user wants to create a new Google Cloud project, choose a project ID and naming co...
--- name: aerobase-lounges version: 3.1.6 description: Airport lounge access and recovery recommendations metadata: {"openclaw": {"emoji": "🏧", "primaryEnv": "AEROBASE_API_KEY", "user-invocable": t
Query Prometheus monitoring data to check server metrics, resource usage, and system health. Use when the user asks about server status, disk space, CPU/memo...
Write Obsidian-compatible .md notes and .canvas files. Use when creating notes, knowledge bases, daily logs, project docs, or canvas diagrams for Obsidian va...
Send and receive encrypted messages and manage handshakes on the Kaspa blockchain using Kasia protocol and mcporter tools.
Continuously captures and applies learnings from errors, user corrections, successful tasks, and periodic reviews to improve agent performance.
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text fr
AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions',...
Generate a well-structured llms.txt file for any business website. Crawls the site, has a short conversation to fill in gaps, and produces an agent-optimized...
Autonomously inspects a live OpenClaw instance across 5 health domains (hardware, config, security, skills, autonomy) and delivers a quantified traffic-light...
AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parall...
Beamer integration. Manage Organizations, Users, Filters. Use when the user wants to interact with Beamer data.
Control and automate browser actions via HTTP API, including navigation, element interaction, data extraction, accessibility snapshots, screenshots, JS execu...
--- name: "stripe-integration-expert" description: "Stripe Integration Expert" --- # Stripe Integration Expert **Tier:** POWERFUL **Category:** Engineering Team **Domain:** Payments / Billing In
--- name: desktop-control description: Control the desktop via CUA computer server API running on port 8000 version: 1.0.0 --- # Desktop Control via CUA Server This skill allows OpenClaw to control
A cognitive growth framework that helps your AI truly know you — and help you know yourself. Includes personality profiling, behavioral pattern detection, re...
Connect with 17 specialized AI mentors for expert guidance on growth, fundraising, sales, product, engineering, operations, finance, legal, hiring, leadershi...