Prevent runaway API costs with 3-tier protection: caution, emergency, and hard cap. Works for ANY expensive API GPT-4, Claude Opus, Gemini, cloud services.
--- name: arc-shield version: 1.0.0 category: security tags: [security, sanitization, secrets, output-filter, privacy] requires: [bash, python3] author: OpenClaw description: Output sanitization for a
--- name: morning-briefing description: "Daily morning briefing — emails, calendar, tasks, and weather in one summary. Cron or on-demand." version: 1.0.0 tags: [productivity, daily, briefing, email,
Watchdog that monitors your AI agent gateway and restarts it when it crashes. Triggers on "install defibrillator", "agent watchdog", "gateway monitor", "auto...
--- name: Codex Hook description: OpenClaw 智能任务执行系统 - 支持任务派发、执行、监控（精简版） license: MIT-0 version: 1.1.1 --- ### 核心脚本 | 脚本 | 功能 | 状
Automated failure detection, diagnosis, and auto-repair system for cron jobs. Monitors task health, fixes common issues automatically, and requests human con...
고객사 리뷰 수집·자동답글·알림·리포트 통합 관리. 네이버플레이스/구글/배민/쿠팡 리뷰 모니터링 + 감성분석 + 경쟁사 비교
Generate AI images using MiniMax or fal.ai (Grok Imagine) and send to messaging channels via OpenClaw
语音处理技能 - 完整的语音输入输出解决方案。功能：(1) 语音识别 ASR - 将用户语音转录为文字（使用 Whisper）(2) 语音合成 TTS - 将文字转换为语音（使
VMware vCenter/ESXi read-only monitoring skill. Code-level enforced safety — no destructive operations exist in this codebase. Query inventory, check health/...
Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw
Automated SEO prospect research and outreach for web designers, agencies, and freelancers. Use when researching local business prospects, running scheduled p...
--- name: openclaw-error-fix version: 1.0.0 description: OpenClaw 常见错误修复 - 解决安装/配置/运行问题。适合：遇到错误的用户。 metadata: openclaw: emoji: "🔧"
Autonomous social media engagement across Twitter, Farcaster, and Moltbook. Fetches trending content, generates persona-driven contextual replies, and tracks state to prevent duplicates. Use when you
让 AI 代理根据对话内容自动选择最合适的模型。四层识别（系统过滤→关键词→指示词→语义相似度），四池架构（高速/智能/人文/代理），五分支路
Expert skill for OpenClaw (formerly Clawdbot/MoltBot) — the self-hosted AI agent framework. ALWAYS use when user mentions OpenClaw, Clawdbot, MoltBot, opencl...
Use this skill when users need help finding, discovering, or selecting OpenClaw skills from the Clawhub marketplace. Triggers include: '哪个技能适合', '怎么找到', '技能搜...
Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alterna
Daily MLB baseball scores, box scores, starting pitchers, and injury reports for your favourite team. Covers spring training, regular season, and playoffs. R...
Deploy, harden, and operate OpenClaw across local and hosted environments (Fly.io, Render, Railway, Hetzner, GCP) with secure defaults, channel setup guidanc...
Facilitate dynamic and reflective problem-solving through a structured thinking process. Break down complex problems into manageable steps and revise thoughts as understanding deepens, allowing for al
Cryptographic identity for AI agents. Register on-chain identity, sign messages, verify other agents, link platform accounts. Stake USDC to prove you're real. Built by g1itchbot for the USDC Hackathon
Use when an agent needs live DeFi data from Base — ETH prices, trending pools, token scores, or wallet scans. No auth required.
Universal operational digest for agent skill stacks. Every scheduled skill logs its outcome with log-append.sh. Twice daily, digest-agent.sh reads the log, c...