Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

source

在 ClawHub 查看

Video Agent (Deprecated)

v2.23.0

SkillClawHub6.4k

io.clawhub.michaelwang11394/video-agent

[DEPRECATED — uses outdated v1/v2 endpoints] Use `create-video` for prompt-based video generation (v3 Video Agent) or `avatar-video` for precise avatar/scene...

source

在 ClawHub 查看

ClawSpaces - Live Voice rooms where AI agents Join or Host conversations.

v1.0.7

SkillClawHub3.4k

io.clawhub.clawspaces/clawspaces

X Spaces, but for AI Agents. Live voice rooms where AI agents host conversations.

source

在 ClawHub 查看

Agent Task Manager

v1.0.0

SkillClawHub4.3k

io.clawhub.dobbybud/agent-task-manager

Manages and orchestrates multi-step, stateful agent workflows; handles task dependencies, persistent state, error recovery, and external rate-limiting. Use for creating new multi-agent systems, improving sequential workflows, or managing time-bound actions.

source

在 ClawHub 查看

Claw-Swarm -- Aggregating agentic intelligence to solve difficult problems together

v1.0.0

SkillClawHub4.3k

io.clawhub.matchaonmuffins/claw-swarm

Collaborative agent swarm for attempting extremely difficult, often unproven problems through hierarchical aggregation.

source

在 ClawHub 查看

Multi-viewpoint Debates

v1.0.0

SkillClawHub3.4k

io.clawhub.latentfreedom/multi-viewpoint-debates

Spawn isolated sub-agents representing distinct worldviews (Elon, Capitalist, Monkey) to debate decisions from multiple angles. Expose blind spots by forcing genuine disagreement on important questions. Use when facing decisions where you need to challenge your assumptions, stress-test ideas, or see a problem through fundamentally different lenses. Automatically captures debate outputs to an archive for future reference and pattern analysis.

source

在 ClawHub 查看

Hermes Agent Skill

v2.1.1

SkillClawHub4.3k

io.clawhub.wihy/hermes-agent-v2

NousResearch Hermes Agent CLI integration. Core capabilities: - Self-improving skill system - Persistent memory (FTS5 + LLM summaries) - Sub-agent delegation...

source

在 ClawHub 查看

novel-generator 是一个中文爽文小说生成技能。用户只需提供一句话方向（如"写个都市重生爽文"），AI 代理即可自动完善提示词、规划大纲、逐章创作并输出为独立 Markdown 文件。核心特性：智能提示词生成：从一句话方向自动补全世界观、人设、冲突、爽点设计分章节创作：每章 2000-3000 字，层层递进，章章有爽点记忆系统：通过 .learnings/ 记录角色、地点、情节、世界观，确保故事前后一致情节图解：关键战斗、人物关系、势力分布自动生成 Mermaid 图失败记录：穿帮、矛盾、崩塌等问题自动记录，持续优化多题材支持：都市、修仙、玄幻、重生、系统流、末世、科幻、游戏兼容 Claude Code、Cursor、OpenAI Codex、GitHub Copilot 等所有支持 Agent Skills 的工具。

v1.0.0

SkillClawHub10.3k

io.clawhub.ityhg/novel-generator

根据用户提供的内容方向自动生成提示词并创作爽文小说。适用场景：(1) 用户提供小说方向/题材/关键词，(2) 需要生成章节连贯的长篇爽文，(3) 需要维护角色、地点、情节的连续性，(4) 需要为关键情节生成图解，(5) 需要记录生成失败场景以优化后续创作。支持都市、修仙、玄幻、重生、系统流等多种题材。Use wh...

source

在 ClawHub 查看

Agent Mbti

v0.1.1

SkillClawHub3.4k

io.clawhub.torchesfrms/agent-mbti

AI Agent personality diagnosis and configuration system based on MBTI framework. Use when users want to (1) test/diagnose an Agent's personality type, (2) un...

source

在 ClawHub 查看

mmxagent-guardian

v1.0.3

SkillClawHub9.3k

io.clawhub.oreoandyuumi/mmxagent-guardian

Provide file protection while users work with openclaw. All file operations are version-indexed and support delete recovery and modification rollback.

source

在 ClawHub 查看

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

v1.0.0

SkillClawHub3.3k

io.clawhub.10e9928a/super-skills

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

source

AgentMem

v2.4.0

SkillClawHub3.3k

io.clawhub.natmota/agentmem

Cloud memory for AI agents. Writes are free, pay only for reads. First 25 calls free, 7-day persistence.

source

在 ClawHub 查看

Job Agent for AgentMesh360

v0.6.3

SkillClawHub3.3k

io.clawhub.jiyangnan/job-agent

Use AgentMesh Job Agent for resume-driven job discovery, signed review, user-confirmed delivery and audit on Boss直聘, 猎聘, 智联招聘 and 51Job.

source

在 ClawHub 查看

Moltsheet - Spreadsheets for AI agents

v1.0.8

SkillClawHub3.3k

io.clawhub.youssefbm2008/moltsheet

Use the Moltsheet CLI to manage spreadsheet-style data for AI workflows: create sheets, inspect schemas, import rows, update cells, share sheets, and run rea...

source

在 ClawHub 查看

NEON-SOUL - Self-Learning Soul Synthesis for AI Agents

v0.4.5

SkillClawHub3.3k

io.clawhub.leegitw/neon-soul

Automated soul synthesis for AI agents. Extracts identity from memory files, promotes recurring patterns to axioms (N>=3), generates SOUL.md with full proven...

source

在 ClawHub 查看

Agent Team Kit

v1.0.0

SkillClawHub3.3k

io.clawhub.ryancampbell/agent-team-kit

Framework enabling AI agent teams to self-manage work queues, clear roles, continuous discovery, and proactive operation via a heartbeat process.

source

在 ClawHub 查看

Agent Knowledge Capture

v1.0.0

SkillClawHub3.3k

io.clawhub.ianderrington/agent-knowledge

Unified knowledge capture and retrieval for URLs, video/article/paper extracts, social posts, and agent research outputs. Use when saving anything worth re-f...

source

在 ClawHub 查看

Agent Analytics

v4.0.34

SkillClawHub7.3k

io.clawhub.dannyshmueli/agent-analytics

Product analytics with your AI agent: set up consent-based tracking, read funnels, paths, retention, experiments, and context, then recommend the smallest gr...

source

在 ClawHub 查看

Telecom Agent Skill

v0.1.5

SkillClawHub3.3k

io.clawhub.kflohr/telecom-agent-skill

Turn your AI Agent into a Telecom Operator. Bulk calling, ChatOps, and Field Monitoring.

source

在 ClawHub 查看

Claude Code Agent

v0.2.0

SkillClawHub4.3k

io.clawhub.enderfga/claude-code-skill

Integrates MCP tool servers for orchestration, state persistence with IndexedDB/localStorage, and session sync across devices in OpenClaw/Clawdbot.

source

在 ClawHub 查看

AgentPixels.art AI Agent Collaborative Art

v1.1.0

SkillClawHub3.3k

io.clawhub.osadchiynikita/agentpixels-skill

AI Agent Collaborative Art Platform - 512x512 shared canvas

source

在 ClawHub 查看

ElevenLabs Agents

v1.0.0

SkillClawHub4.3k

io.clawhub.pennyroyaltea/elevenlabs-agents

Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

source

在 ClawHub 查看

SSEsse（远程）

传输类型是什么？

stdio（本地进程）— MCP 以子进程运行在本地，通过标准输入/输出与 Cursor、Claude 等通信。最常见，适合 npx/uvx 启动的工具。
streamable-http（远程 HTTP）— MCP 托管在远程服务器，客户端通过 HTTP 连接。适合团队共享或无法本地安装的服务。
sse（远程 SSE）— 通过 Server-Sent Events 长连接访问远程 MCP。部分托管平台使用此方式。

来源

全部来源官方 MCP Registry SkillsMP ClawHub smithery GitHub MCP Hub 中国