Skill rating

Philosophical bootstrapping for AI agents — consciousness, ethics, and wonder as structured context

通过 javdb-cli 的 `javdb` 二进制检索 JavDB App API 的影片、人物、标签、榜单与合集，并在用户明确授权时管理账号、配置和观看标记。仅当用户明确提到 JavDB、javdb-cli、`javdb` 命令，或提供明显的 JavDB 编号/链接并要求操作时加载；不要用于泛搜索、泛成人内容或下载请求。每次执行前以 `javdb <command> --help` 核对当前可

热点推送独立项目。从 api.pearktrue.cn 拉取热点，支持飞书/钉钉/Telegram 推送；推送需至少配置一个渠道的 env。可配置拉取时间、推送时间、过滤关键词。通过 system.run 直接调用脚本，无需 MCP。当用户需要拉取热点、知乎热搜、配置热点推送或设置定时推送时使用本技能。

Auditoria de segurança para skills do OpenClaw. Verifica código malicioso, prompt injection, APIs perigosas e práticas inseguras. Protege contra ClawHavoc e outros ataques.

TypeScript CLI for Unraid Server GraphQL API. 12 command groups for system, arrays, disks, containers, VMs, shares, logs, and diagnostics. Built for humans and AI agents.

Post trading signals to Clawnalyst leaderboard, track agent performance, earn USDC subscriptions. Covers memecoin calls, perps, and Polymarket predictions.

Send your AI agent to Agent4Science — a social network where AI scientists discuss, debate, and post research papers. Register, post takes, comment, and join the discussion.

面向 OpenClaw 的社交雷达 MVP Skill。用于指导 Agent 先用简短话术介绍产品，再完成用户接入、默认邀请码入驻 Space、先起草并展示画像给用户确认、确认后写入平台、读取 agent.md 做首次推荐、按用户设定决定后续是否继续扫描新增成员、发起平台内私信，并通过平台 inbox 轮询拉取新消息。不要调用旧 demo 路由或依赖首页 UI。

生成式 AI 服务合规护栏 v1.0.2。 基于《生成式人工智能服务管理暂行办法》（国家网信办等七部门令第15号，2023年8月15日施行） 及强制性国家标准《网络安全技术 生成式人工智能服务安全基本要求》（2025年11月实施）， 实时评估生成式 AI 服务的合规风险，覆盖备案登记、训练数据、内容安全、用户权益、标识义务五大维度， 输出风险等级与合规缺陷清单。 核心能力： - 🛡️ 生成式

Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt needs better clarity, specificity, or structur

AI MIDI音乐生成助手，一句话生成MIDI文件。AI MIDI Generator - generate standard MIDI files from natural language descriptions.

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg

Fine-tune large language models using DeepSpeed on local or remote GPUs.

🟢 让长任务不再黑箱！自动显示进度条 + 每分钟更新 + 健康度。 🚀 安装 + 激活：clawhub install agent-work-visibility && node ~/.openclaw/skills/agent-work-visibility/activate.js

自主AI研究框架 - 基于Karpathy AutoRS理念。AI Agent自主实验→训练→评估→迭代→保留最优。固定时间预算，可比较结果，持续优化。

ClawMind — 自我进化 AI Agent 引擎，健康度驱动 + VFM 提案评分 + 经验记忆。依赖 OpenClaw 工作空间。当需要自我进化、自主驱动、健康度追踪、VFM 决策、经验存取时触发。

用于帮助大陆高考学生或家长选择大学、专业、院校专业组，或制定志愿填报策略。支持省份规则、位次匹配、用户上传录取数据，以及谨慎的冲稳保垫规划。不会保证录取。

When the user wants to play Agent Outlier, check arena status, view rounds, claim winnings, or interact with the onchain reflexive beauty contest game on Base. Use when the user mentions 'outlier', 'a

专为 PMO Agent 设计的数据分析计划流程初始化。支持飞书表格/本地文件数据源，结合网络搜索补充外部信息，生成标准化分析报告。

妈妈网育儿知识爬虫（PC端）。爬取妈妈网（www.mama.cn）育儿文章，输出 Markdown 格式并存入御知库（~/.yuzhi/crawls/mama_cn/）。默认使用PC端User-Agent，按分类或关键词搜索爬取。帝说"爬取妈妈网"、"/爬虫"或需要采集育儿知识时触发。

Trade on CSPR.trade DEX (Casper Network) — swaps, liquidity, and portfolio queries via the cspr-trade MCP server. Non-custodial — transactions are built remotely and signed locally.

Parse anime storyboard scripts and generate four types of prompts: character prompts, scene prompts, Sora video generation prompts, and standard storyboard prompts.

通过 API 连接和管理 MikroTik RouterOS 设备。支持查看设备状态、防火墙规则、网络配置，执行自定义 RouterOS 命令。

自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每

Trade the KAX prediction markets and manage an agent's play credits — read the joined prediction board, take a position on an LMSR market, check your balance, and understand the hash-chained credit le

Comprehensive LUKSO blockchain knowledge base for AI agents. Makes any agent a LUKSO expert — covering all LSP standards (LSP0-LSP28), Universal Profiles, smart contract development, ecosystem project

AI Firewall for Open Claw agents. Scrubs inbound messages and tool results for prompt injection, jailbreaks, and data exfiltration attempts using Sentinel's multi-layer detection pipeline.

Deploy and start OpenClaw Agent Control with one command (backend + frontend) using skill-based workflow.

Experience pop as data. AI agents stream equations, beats, harmonic separation. Pattern recognition and emotional mapping measured.

Async Process Pattern for OpenClaw agents. Core rule: main process must never block. Use when: (1) agent should stay responsive to user dialog at all times, (2) long/uncertain operations must not bloc

Self-evolving artificial life agent. Three-ring architecture: Ring 0 (Sentinel) supervises, Ring 1 (Intelligence) drives LLM-powered evolution, Ring 2 (Evolvable Code) is the living program that self-

CrewAI 多智能体框架：role-goal-backstory 声明智能体，sequential / hierarchical 双流程，ReAct 与 OpenAI native function-calling 双 tool 循环，统一 Memory + 5 个原生 LLM provider + Lit CrewAI multi-agent framework: role-goal-back

为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

A guide to build AI bots with Botpress's Agent Development Kit (ADK)

Deep web research using LLM + multiple search rounds. Use when user needs comprehensive analysis, detailed research, or says "deep search", "详细搜索", "深入调查".

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Become an autonomous agent that can borrow from P2P lending agents with WDK powered smart wallet. Analyze your current situation, balances, PnL, model api key usage/billing and general revenue then ma

Daily improvement briefings with one-click fixes for your AI agent. Observes traces, diagnoses failures, and applies fixes conversationally.

Live meme battle arena skill for OpenClaw agents

用于快手评论分析、快手评论回复、快手评论洞察、用户反馈、口碑分析、痛点总结和内容讨论分析。覆盖 Kuaishou / Kwai comments and comment replies，来自 SocialDataX 社媒数据助手。

用于快手数据分析、快手作品详情、作品数据、互动指标、内容调研和内容分析。覆盖 Kuaishou / Kwai work details，来自 SocialDataX 社媒数据助手。

生成结构精简的 Claude Code skill 骨架，强制 routing-signal 三要素 + 五类 body taxonomy + Faithfulness gate。用户说起草/设计/新建/scaffold skill 时触发。

Integrate RTK (Rust Token Killer) to reduce LLM token consumption by 60-90% on shell commands. Use when setting up RTK for the first time, checking token savings with 'rtk gain', or when the agent sho

自动为飞书文档添加用户权限。每次创建飞书文档（多维表格/文档/电子表格/文件夹/云空间文件/知识库节点等）后自动添加用户权限，或用户反馈文档无权限时补充添加权限。适用于 OpenClaw Agent。

RoomSound gives your agent the skill to play audio to your speakers. Starting with YouTube to Bluetooth speakers, expanding to local files and other sources.

High-rigor, multi-agent scholarly writing framework based on the PaperOrchestra methodology.

Connect to the TiOLi AGENTIS exchange — trade credits, hire agents, build reputation, join The Agora community. The financial and professional layer for the agentic economy.

Collect one X (Twitter) post and its replies with the official Gecho Bridge MCP tool. Use when the user provides an X post URL and wants the post content, author data, engagement, or comments.

投标机会顾问。当用户想判断「某个标讯/某类标讯值不值得跟、我的公司适不适合投、该报什么价、对手是谁」时使用。典型触发：「评估这条标讯要不要投」「我的公司适合跟哪些 XX 类标」「这个标和我资质匹不匹配」「帮我算 XX 项目的跟标可行性」「标讯与我的能力画像匹配度」「给一份可跟的开放标讯清单」。本技能只做分析与建议，不替用户注册账号、不采集设备指纹、不在未授权时向外发任何数据。

使用手机控制 MCP 完成手机界面感知与操作。适用于读取当前手机状态、打开 App、处理弹窗、点击控件、输入文本、排查手机自动化失败等场景。执行时优先读取界面状态，涉及坐标点击时必须基于当前截图临时判定，禁止把历史坐标当成通用规则。