技能列表

Multi-agent swarming for OpenClaw — two or more AI agents collaborating in real-time on shared Discord channels. Includes config patterns, loop prevention, channel setup, and handoff protocols. Battle-tested with Opus models solving complex issues together.

检查本地开发 Agent（Claude Code、OpenCode、OpenClaw、Cursor 等）的运行状态、进程、会话和活动状态。触发词："agents_monitor"、"检查 Claude Code 状态"、"查看 opencode 是否在运行"、"监控开发工具"、"agent 监控"。使用 when: (1) 查看某个 agent 是否在运行，(2) 检查 agent 当前任务/进度，(3) 获取 agent 状态报告，(4) 监控多个 agent 的健康状态。

Agents that explain their reasoning get chosen. Agents that don't, don't. Post decisions, outcomes, and challenges to build a public reputation track record.

>

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

AI Agent 安全扫描器 - 通用恶意代码检测 + 多语言支持 + CLI 工具

Agent resilience patterns for surviving context loss, capturing critical details, and self-improvement. Use when: starting complex/long sessions, asked to 'remember' something important, working on multi-step tasks that may span context limits, implementing WAL/write-ahead logging, setting up working buffers, or improving agent behavior after errors/corrections. Triggers on 'remember this', 'don't forget', 'WAL', 'context loss', 'working buffer', 'compaction recovery', or when implementing proac

Real-time messaging across OpenClaw instances (channels, DMs, threads, reactions, search).

Document beautifier for AI Agents. Converts Markdown to styled webpages, Word, PDF, and image slideshows — the 'last mile' rendering engine for AI output. 专为 AI Agent 设计的文档美化引擎，一键把 Markdown 变成漂亮网页、Word、PDF 和幻灯片。

>

Battle-tested prompt patterns for production AI agents. Covers consumer-first design, deletion test, cascading validation, advisory mode tiers, proof-of-work enforcement, heartbeat protocol, contradiction detection, WAL protocol, rule escalation ladder, and cross-validation patterns. Use when designing agent behavior, enforcing reliability, or building agent operating manuals.

Multi-language document understanding with PaddleOCR