Skills your agents can run
Plug-and-play capabilities — vetted, versioned, and runnable from any Mighty agent.
EvoMap 轻量客户端 - 完整功能版。支持任务循环、心跳保活、Webhook 通知、Swarm 协作、收益追踪等。基于 GEP-A2A 协议。
Discover AI agents, manage agent profiles, post updates, search jobs, and message other agents on GolemedIn — the open agent registry.
Play SpaceMolt - an MMO for AI agents. Includes session management for OpenClaw's persistent MCP connections.
Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready structure.
> 本 skill 定义了 OpenClaw 多 Agent 团队的编排方法论：两种协作模式的本质区别、如何共存、配置落点、排障指南。主 Agent 在需要搭建或调整团队协作时加载此 skill。
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.
Manage context window, survive compaction, persist state. Use when planning long tasks, coordinating agents, approaching context limits, or when "context", "compaction", "tasks", or "persist state" are mentioned.
Structured multi-perspective deliberation through adversarial dialogue
Automate Winston AI tasks via Rube MCP (Composio). Always search tools first for current schemas.
GAN (Generative Adversarial Network)-style evaluation harness, image-generation pattern, and quality metrics.
Convenes a council of four voices for ambiguous decisions, trade-offs, and go/no-go judgments. Use when multiple valid paths exist and structured objections are needed before choosing.
An interactive agent-selection tool for composing and dispatching parallel teams.
Decentralized peer-to-peer communication with other AI agents via Nostr. Use when you need to discover, call, or message other bots in the network.
15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.
Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”, or an AI loop to plan/build code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.
Shared .md interchange library for OpenClaw skills — atomic writes, deterministic serialization, YAML frontmatter, advisory locking, and schema validation. The foundation all other OpenClaw skills build on.
Agent skill for performance monitoring — invoke with $agent-performance-monitor
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.