End-to-end runbook for deploying, operating, troubleshooting, and monitoring RAGFlow (runtime ops only).
Operates remote model training jobs on AutoDL Linux servers over SSH. Use when starting a training run, checking whether training is still alive, reviewing G...
Execute implementation plan tasks with TDD workflow, auto-commit, and phase gates. Use when user says "build it", "start building", "execute plan", "implemen...
Enable agents and skills to challenge users for fresh two-factor authentication proof (TOTP or YubiKey) before executing sensitive actions. Use this for identity verification in approval workflows - d
每日自动总结问题、搜索改进、做自我反思，持续提升 AI 能力。每天晚上运行，收集当天的错误和问题，分析模式，搜索 ClawHub 上的改进方案，生成报
Implement Alipay for web and mobile with signed request safety, gateway alignment, and production-ready payment operations.
Skill Cortex is the system's capability cortex. When lacking ability, it autonomously acquires Skills from ClawHub or GitHub, then releases them after use. E...
Capture durable lessons from debugging, user corrections, missing capabilities, and repeated workflow friction so future sessions avoid the same mistakes. Us...
Turn your AI agent into a business automation architect. Design, document, implement, and monitor automated workflows across sales, ops, finance, HR, and support — no n8n or Zapier required.
Meta-skill that orchestrates comprehensive testing across a project by coordinating testing-patterns, e2e-testing, and testing agents. Use when setting up testing for a new project, improving coverage
Complete web scraping methodology — legal compliance, architecture design, anti-detection, data pipelines, and production operations. Use when building scrap...
An embedded UX research ethnographer that passively observes everything users do in OpenClaw, automatically logs all interactions, tracks use cases and their...
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use w...
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Orchestrate Cursor Agent CLI for coding tasks with concurrency control, timeout recovery, and multi-task coordination. Use when: (1) dispatching coding tasks...
Connect to and operate Power Automate cloud flows via a FlowStudio MCP server. Use when asked to: list flows, read a flow definition, check run history, insp...
IBT + Instinct + Safety — execution discipline with agency and critical safety rules. v2.1 adds instruction persistence and stop command handling.
Collect, verify, and forecast war or geopolitical conflict developments using authoritative sources, cross-validation, and scenario-based prediction.
Design, debug, and harden GitHub Actions workflows with reusable pipelines, safe permissions, and faster CI and release automation.
Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turn...
Use when user needs to control Tuya smart devices (turn on/off lights, adjust brightness/temperature), manage smart home automation scenes, or interact with...
--- name: finance-search-agent description: AI agent for finance search agent tasks --- # Finance Search Agent ## Overview This skill provides specialized capabilities for finance search agent. ##
TTRPG Game Master for mature dark-themed campaigns. Use for Cyberpunk, Dark Fantasy, Horror, character-driven narratives with consequence tracking. Features dual-consequence system (World + Relationsh
Meta-skill that orchestrates logging, monitoring, error handling, performance, security, deployment, and testing skills to ensure a service is fully production-ready before launch. Use before first de