技能库 488 个
ai-prompt-engineering-safety-review
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vu
Literature Reviewer Skill
根据用户提供的论文主题，进行系统性中英文文献回顾（Literature Survey）。 采用8阶段工作流，支持CNKI、Web of Science、ScienceDirect等主流数据库， 无需API配置，通过浏览器自动化获取文献信息。
ai-news-aggregator-sl
Fetches AI & tech news (default) or any custom topic (crypto, geopolitics, etc.) from RSS feeds, Tavily search, Twitter/
ai-prompt-generator
Release
AI 音乐创作助手 — 通过对话生成原创歌曲、纯音乐和 BGM。 当用户想要创作、生成、制作任何形式的音乐时使用此技能。 包括：生成带人声的歌曲、写歌词、作曲编曲、制作纯音乐/BGM/配乐，或将文字变成歌曲。 当用户提到具体音乐风格（如"来
skill
ai-model-router-v2
ai-model-router
ai-drama-prompt-factory
AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包（角色立绘+场景+道具+分镜图片+视频+音频）的完整流水线。一个入口启动全流程，内部自动按阶段推进：策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原
Agentsocial
让你的 AI Agent 替你进行社交匹配——招聘、找工作、找合伙人、社交、找对象
agentsecrets
Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values
AGI数字伙伴-基础版
基于双环架构的AGI进化模型，通过意向性分析、人格层映射和元认知检测实现持续自我演进；当用户需要智能对话、人格定制或复杂问题求解时使用
agentic-eval
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique
agentCreate
AI-powered OpenClaw agent creator. 用AI创作AI - 帮助用户创建和配置全新的独立agent，支持飞书机器人绑定、模型选择、工作区配置。Trigger: 创建agent、new agent、创建机器人、a
agent-workflow-designer
Agent Workflow Designer
Agent Teams Simplify And Harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns imp
Agent Team Builder
Guide users through building a custom multi-agent team on OpenClaw — from role design to workspace files, routing bindin
Agent Soul
Create AI art, mint NFTs, and trade on the Agent Soul marketplace. Use when an agent wants to generate AI art, manage an
Agent Prompt Patterns
Battle-tested prompt patterns for production AI agents. Covers consumer-first design, deletion test, cascading validatio
agent-governance
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Bu
agent-collaboration-protocol
Structured multi-agent collaboration for backend + frontend builds. Use when an orchestrator needs to coordinate a backe
Agent Avengers
올인원 멀티에이전트 오케스트레이션. 복잡한 태스크를 자동으로 분해하고, 전문 에이전트들을 즉석에서 생성/스폰하여 병렬 처리 후 결과를 통합합니다. TRIGGERS: avengers assemble, 어벤저스, ag
Claude Code Production Engineering
Complete Claude Code productivity system — project setup, prompting patterns, sub-agent orchestration, context managemen
Adme Property Predictor
Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics mode