Configure OpenClaw multi-agent routing for Feishu multi-account setups. Use when users need two or more Feishu bots (different appId/appSecret) to run on iso...
--- name: CryptoTraveler version: 1.3.2 description: Book flights, hotels, and eSIMs on cryptotraveler.com with Bitcoin and other cryptocurrencies. homepage: https://www.cryptotraveler.com flight
AI desktop agent — control any app on Windows/macOS from your OpenClaw agent. Send natural language tasks to the Clawd Cursor API and it handles everything:...
Enables AI agents to log immutable, encrypted audit trails on Bitcoin SV for persistent memory, self-reflection, and on-chain economic tracking.
三层记忆系统自动管理长对话记忆，支持跨会话检索、结构化存储和智能压缩，提升记忆连续性与上下文管理效率。
Simple CRM for freelancers. Track contacts, projects, invoices, follow-ups, communication history. All through conversation with your agent.
Detects phantom dependencies — references to things that no longer exist, ghost state that lives in the gaps between modules, and invisible wires that connec...
MongoDB-backed long-term semantic memory for recalling, storing, searching, and managing facts, decisions, and user preferences across sessions.
Diagnose and triage cron job failures. Checks job states, identifies error patterns, prioritizes by criticality, generates health reports. Triggers on: cron...
防护间接提示词注入攻击（Indirect Prompt Injection）。当处理网页内容、搜索结果、邮件、社交媒体等外部来源信息时触发。用于识别和防范外部内容中隐
Automated security auditing for OpenClaw projects. Scans for hardcoded secrets (API keys, tokens) and container vulnerabilities (CVEs) using Trivy. Provides...
Qualify leads, prospects, clients, candidates, projects, opportunities, and requests before deeper time, money, or effort is committed. Use when someone need...
Control macOS GUI apps visually — take screenshots, click, scroll, type. Use when the user asks to interact with any Mac desktop application's graphical inte...
macOS GUI automation and desktop control for OpenClaw, powered by Hammerspoon. Gives your agent full access to interact with the Mac desktop — query windows,...
Configurable quality evaluation for AI agent outputs. Define criteria, run evaluations, track quality over time. No LLM-as-judge, no API calls, pattern-based...
Adds an "OAuth" settings tab to the OpenClaw Control UI for connecting AI model providers. Supports Anthropic Claude Pro/Max subscription tokens (setup-token...
Cross-platform mouse/keyboard automation skill. Supports mouse control (move/click/drag/scroll), keyboard control (key press/hotkeys/type text), screen opera...
Transform raw AI output into platform-ready content with proper formatting, metadata, and cleanup. Markdown, HTML, plain text, and structured data output.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Deep Lark integration skill. A Digital Command Center powered by a Coordination Diagnosis Engine. It balances speed and tact across chat, approvals, meetings...
Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to ch...
Design and build OpenClaw skills. Use when asked to "make/build/craft a skill", extract ad-hoc functionality into a skill, or package scripts/instructions for reuse. Covers OpenClaw-specific integrati
Automated backup in 3 layers: daily timestamped snapshots, secondary drive mirror, and emergency conversation export.
--- name: elevenlabs-calls description: Make AI phone calls using ElevenLabs Conversational AI and Twilio. homepage: https://elevenlabs.io/docs/agents-platform/overview metadata: {"clawdbot":{"emoji":