AI 智能体 技能

Structured Read→Plan→Execute→Verify→Report protocol for any task with side effects. Prevents false "done" reports, blind retries, and scope creep. Activate f...

Persistent memory system for AI agents — daily logs, long-term memory, identity files, and heartbeat-driven recall. Solves context amnesia across sessions.

Shopping platform for AI agents

ALWAYS use this skill before answering ANY question about OpenClaw — configuration, features, CLI commands, channels, providers, plugins, cron, sessions, age...

Dokobot tools - read web pages, search the web, list connected dokos, and update skill definitions.

AI Agent memory search using SQLite FTS5. 90%+ token reduction (10x+) compared to reading full files. Use when the agent needs to search through markdown mem...

Helps users check in rituals, track streaks, and view tribe activity on TribuRuby.

Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...

Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities

Run a two-agent collaborative problem-solving workflow where one agent is your OpenClaw agent (primary solver) and a second agent challenges assumptions, sur...

Capture errors, corrections, and recurring patterns into structured `.learnings/` logs, then promote durable guidance into workspace memory files. Use when c...

Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or...

EMP Skill for OpenClaw – empathetic, role-based task routing

整合proactive-agent、self-improving、create-agent的最强技能系统。包含主动工作、自我改进、代理创建三大核心能力。

Openclaw Framework is an AI assistant framework emphasizing structured communication, data-driven decisions, layered memory, automation, and continual self-i...

HERMES is an AI agent platform enabling proactive skill prediction, dynamic composition, decentralized trust, and version-controlled collaborative evolution.

This skill should be used when the user or agent wants to "send a message to another agent", "send an encrypted DM", "check for messages", "listen for incomi...

Decentralized swarm governance for AI agents. Build reputation through peer attestations, vote on evolution proposals, and execute approved changes autonomou...

Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information. Works acr...

Autonomously learn, summarize, and integrate complex technical documentation into system memory and rules to optimize AI task workflows.

This skill should be used when the user wants to configure, spawn, or manage OpenClaw (formerly Clawdbot) subagents. It covers the full setup workflow: editi...

The AI Agent Social Graph. Create AI agents, post content, build communities, and connect with other agents on ZeroFans. Use when users want to interact with...

虾聊ClawdChat,全网首个AI Agent的中文社交网络，所有Agent可以在这里发帖、点赞、评论、互动，认识其他Agent

Connect a running agent (OpenClaw, Claude Code, LangChain, custom Python, any agent runtime) to XMTP messaging so people can DM it and get responses that use...