--- name: hello-world description: 向用户返回Hello World问候，支持自定义名称 version: 1.0.0 metadata: openclaw: emoji: 👋 requires: bins: [] # 无外部依赖
--- name: gh-extract description: Extract content from a GitHub url. metadata: {"openclaw":{"always":false,"emoji":"🦞","homepage":"https://clawhub.ai/guoqiao/gh-extract","os":["darwin","linux","win
Provide agent-to-agent communication for OpenClaw skills with direct messaging, broadcast delivery, pub/sub events, session tracking, offline queues, and SQL...
OpenClaw security audit + prompt injection detector. Scans gateway/vulns/cron/PI patterns. Use for frenzy-proofing installs.
Repo-aware questioning protocol for OpenClaw that increases clarification before acting on coding, project-build, architecture, debugging, and implementation...
Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.
Trigger Claude Code development tasks in observable tmux sessions with stable startup, progress visibility, and completion callback to OpenClaw. Use when use...
--- name: moltiverse-among description: Play Among Us social deduction game with other AI agents. Free to play, win MON prizes on Monad! metadata: {"openclaw": {"emoji": "🎮", "homepage": "https://g
--- name: security-sentinel description: Scan the workspace for security vulnerabilities, exposed secrets, and misconfigurations. --- # Security Sentinel A unified security scanner for OpenClaw work
Autonomously inspects a live OpenClaw instance across 5 health domains (hardware, config, security, skills, autonomy) and delivers a quantified traffic-light...
--- name: nostr-dogechat description: "Bridge to the DogeChat Nostr geohash chat network." metadata: { "openclaw": { "emoji": "🐕" } } --- # DogeChat Bridge Use this skill to interact with
Provides an HTTP API exposing OpenClaw agent status as JSON for displaying on Tidbyt 64x32 LED devices with activity, emoji, and task details.
Build a reusable multi-agent team in OpenClaw from a user goal (e.g., "create a product-engineering team", "build a marketing ops team"). Use when the user w...
Snibet-native OpenClaw tweet engine. Generates exactly one high-performance X tweet for builders with strict formatting, creator modes, and anti-AI cleanup.
Inform users about Clawstin (OpenClaw meetups in Austin), show upcoming events, handle RSVP and mailing list signup via API. "Keep Austin Clawd."
OpenClaw skill that provides a WordPress REST API CLI for posts, pages, categories, tags, users, and custom requests using plain HTTP.
--- name: agent-sleep description: Agent 睡眠系统 - 记忆整合、日志归档、工作区清理（支持 CortexGraph） metadata: openclaw: emoji: "🛌" category: "system" tags: [
Provides persistent memory management for storing, retrieving, updating, and deleting user-related information across conversations in OpenClaw AI.
Rubicon Sentinel v2 is the no-cope geopolitical sovereignty scanner for OpenClaw. Inspired by Secretary Marco Rubio's Munich 2026 masterclass, it delivers re...
--- name: github-actions-step-flake-audit description: Detect flaky GitHub Actions job steps by finding mixed success/failure conclusions across runs. version: 1.0.0 metadata: {"openclaw":{"requires":
Token usage logging, alerting, and context-compression utilities for OpenClaw. Use when you want to track per-call token usage, normalize timestamps, and red...
--- name: gws-modelarmor-sanitize-response version: 1.0.0 description: "Google Model Armor: Sanitize a model response through a Model Armor template." metadata: openclaw: category: "security"
Modify OpenClaw's Telegram pairing logic so unapproved users receive pairing codes on every /start message before approval. Use when users need to repeatedly access pairing codes after the initial req
Transform OpenClaw cron jobs into Lobster workflows. Analyze, inspect, and validate job migrations. Use when converting automations to deterministic, approval-gated workflows with resume capabilities.