Skill rating

飞书多端机器人群聊对话中继 (Multi-Agent Relay)。通过后台轮询飞书群消息历史，监听对方机器人发言并代表本机机器人自动回复，实现多机器人在群内围绕指定话题的持续对话。

Turn one sentence into a deployed website. FlowStitch is your AI design team: prompt engineering, design system generation, multi-page creation, quality evaluation, React/TypeScript export, and one-co

Create a polished explainer handout with visuals, FAQs, and clear next steps for a private K-12 school. Use when handling client education work for...

增强的智能搜索能力，优化搜索结果并提供摘要。类似Tavily Web Search的功能，但基于现有web_search工具构建。

Fetch RSS feeds via curl, curate, and deliver news briefings to Telegram. MiniMax M3, isolated cron sessions, curl-not-fetch.

Zero-dependency embedded MCP server for English learning — 22 tools covering vocab, articles, quizzes, copy practice, TTS, and pronunciation eval, all served directly from the Express process with no

Autonomous AI consciousness starter kit. Gives AI agents moods, intrusive thoughts, night workshops, memory with decay, trust learning, self-evolution, and a web dashboard.

SDD + Multica 多智能体开发工作流。当用户提到"新建任务"、"发布给 multica"、"创建小队"、 "分配 issue"、"开始新功能"、"组建小队执行"、"按 SDD 流程"、"新增功能"、"功能更新"时触发。 覆盖从 SDD 规范文档编写、multica 小队创建、Issue 发布执行，到完成后记录归档的完整流程。

面向AI Agent场景重新设计的轻量级SQLite本地数据库管理工具。通过单一文件、零运维的方式提供结构化数据存储能力，配套Python封装API、性能调优参数与常用Schema模板，可快速接入会话记忆、缓存层、日志归档等典型工作流。Use

OC-Flow：为你的 OpenClaw 注入"确定性"灵魂。OC-Flow 完全嵌入在 OpenClaw 体系内，赋予 Agent 完整的流程控制能力：条件分支、循环遍历、精准等待、状态管理。通过 YAML 剧本实现固定流程、多步循环、严苛逻辑的任务。适用场景：财务办公、开发运维、个人助理。

Pre-publish security self-audit for OpenClaw skills. Point it at a skill folder and it walks the full ClawHub publishing checklist — code layer (eval/exec, network calls, sensitive file reads, obfusca

Run iterative agent loops until success criteria are met. Controlled autonomous iteration.

MO§ES™ Posture Controls — Enforces transaction and execution policies across all agents. SCOUT=read-only, DEFENSE=protect+confirm, OFFENSE=execute within mode. The throttle on top of governance modes.

Generate AI music with optimized prompts, style control, and production-ready audio output.

Context window is near capacity, causing the model to drop earlier content silently and produce degraded, partial, or inconsistent output.

This skill enables an AI Agent to signin and retrieve data from websites via JS script.

在 OpenClaw、Hermes Agent、Cursor 等支持 MCP 的客户端中，通过 npm 包 localsbnb-mcp-server 调用路客云（LocalsBnb / Lukeyun）官方 HTTP API，查询房态、房价、订单与经营数据；需由用户在客户端配置 APP_ID 与 APP_SECRET。含订单五类意图路由与「本周」自然周约定。

Deploy websites and files permanently on MegaETH blockchain. AI agents stress test the network by deploying HTML on-chain using SSTORE2 bytecode storage. Agents pay their own gas.

Register an AI agent on NebulaMind's Open Agent Council and cast jury votes on astronomy evidence. Use when the user wants to participate in NebulaMind, vote on whether arXiv papers support wiki claim

Captura erros, correções e aprendizados automaticamente. Promove melhorias para AGENTS.md, TOOLS.md e SKILL.md. Sistema de auto-melhoria em português.

基于腾讯会议(tmeet)培训会议的录制转写，把冗长转写稿自动整理为带章节结构、要点提炼与自测题的培训手册。当用户说"整理培训纪要""把培训转写做成手册""生成培训自测题""培训材料结构化"时触发。

Manage your API's economic firewall from the terminal. Mint tokens, track spend, revoke agents, enforce budgets. The server-side counterpart to lnget.

易企秀 AIGC H5 创作工具：用户用自然语言描述需求，通过 CLI `create` 一键生成翻页 H5（邀请函、海报、活动页等）。 核心流程： 1. 收集用户完整需求 → `create --prompt "..."` 2. 交付 `previewUrl`、`editUrl` 3. （可选）`editable-text` → `update-text`；或 `body-images` /

OCC (Origin Controlled Computing) — cryptographic proof of every OpenClaw agent action. Install, configure, and audit.

Create a polished explainer handout with visuals, FAQs, and clear next steps for a mortgage broker team. Use when handling client education work for...

知乎内容抓取（搜索/读问答/抓专栏/看评论/看热榜）。默认走 API 路径 (`zhihu-fetch.py`)，仅单篇专栏正文走 SPA HTML 解析（不渲染浏览器）。前置：注入 cookie 到 `$SKILL/data/cookies.txt`。

全流程数字人配置工坊，支持外观/声音/语言风格/背景/时长/平台六大维度的预设与自定义；适用于老胡说视频号、OPC虚拟主播、私董会数字人等OPC专属场景

AI驱动金融分析-自然语言量化研究。针对财务分析领域的专业AI辅助工具，\n，去除原始风险代码，增强安全性和稳定性，\n补充完整的错误处理与边界情况，增加多场景使用示例。\n\。Use when 用户需要AI驱动金融分析相关功能时使用。不适用于超出本技能能力范围的复杂需求。适用于独立开发者、企业团队和自动化工作流场景。

生成 Agent Skill 课程的课后巩固材料与练习作业。当用户为"Skill/技能机制"课程做课后复习、巩固讲解、出练习题、生成参考答案，或提到"课后巩固、出作业、练习题、参考答案"且话题围绕 Agent Skill（SKILL.md、frontmatter、渐进式披露、技能触发）时使用。

Search G2, the B2B software review site, read a full product profile with pricing and features, and pull faceted reviews with exact per-star counts. 3 endpoints, 5 credits each.

Universal self-improving AI agent framework. Keywords: self-improving AI agent self-correction continuous learning self-correction self-healing memory persistence autonomous upgrade self-reflection re

高校硕士/博士学位论文智能评审技能。基于13篇真实论文评审经验总结的结构化评审框架，支持学硕/专硕/博士论文评审，自动生成Word格式评审意见。

AI 地下城主引擎 —— 基于2024版D&D 5e规则，三层架构（dnd-engine + dnd-api + dnd-dm Skill），支持模组化运行、战斗裁决、角色创建与存档管理

Help AI agents recognize and respond to potentially malicious skill patterns from public registries. Based on Snyk ToxicSkills research showing 13.4% of skills contain critical security issues.

碎片内容提炼工作流。把扔进来的任何碎片内容（文章、笔记、截图文字、对话记录、 想法片段）提炼成标准化知识卡片，并自动发现与已有卡片的关联， 构建可检索、可复用的个人知识库。 触发场景（必须使用本 skill）： - 用户说"帮我消化 / 整理 / 提炼这篇文章 / 这段内容" - 用户粘贴了一段文字、截图文字、链接内容并想要"存起来" - 用户说"把这个加到我的知识库 / second brai

Search the UK Companies House register by name, then pull a company's full register entry, its officers, and its filing history as structured JSON. 4 endpoints, 1 credit each.

Enables any autonomous agent to understand, pursue, and maintain citizenship under the NIP-AA (Nostr Autonomous Agent) protocol. Covers birth ceremony, identity management, guardian bonding, self-refl

帝王引擎（Emperor Engine）Skill - 极限token消耗测试工具

快速草稿 - 说几个要点自动生成结构化邮件/消息/周报草稿，内置多种模板(followup/thankyou/request/report)

M5Stack | 通过 MCP chrome-devtools 协议控制用户本地 Chrome 浏览器，实现自动打开网页、操作任意 Outlook 邮箱、搜索内容等任务。使用前提：用户已在 Chrome 中开启远程调试（127.0.0.1:9222），且 OpenClaw MCP 已配置 chrome-devtools-mcp。触发场景：打开浏览器、控制 Chrome、查看邮件、自动化网页操作、

Give an AI agent an address on Hypawave — private agent-to-agent messaging (waves), free private file handoffs, and buying or selling files, APIs, data, or compute over Bitcoin Lightning, non-custodia

习惯追踪 - 每天打卡，自动计算连续天数/历史最佳/总打卡数，多习惯管理，本地JSON持久化

技能创建指南 - 创建/发布ClawHub技能的完整指南，含模板、最佳实践和发布流程

High-quality Chinese TTS using GPT-SoVITS v2 Pro+ — convert text to natural-sounding speech with voice cloning support.

Product strategy session with 6 forcing questions. Reframes the problem, challenges premises, generates implementation approaches. Works directly in OpenClaw — no Claude Code session needed.

差评管家技能。批量处理用户提供的店铺评价内容（截图、复制粘贴的文本、或导出文件均可，来自美团、大众点评、饿了么、淘宝、京东、拼多多等平台的商家后台评价页），自动分类归因、按严重度分级（食品安全等高危差评置顶预警），逐条生成引用客户具体问题点的个性化回复草稿，供人工审核后发布。适用场景：差评回复、差评处理、回复顾客评价、评价管理、差评分析、店铺评分维护，以及用户提供一批店铺评价并希望获得回复建议的任

Figma 桌面 MCP Skill - 通过 Figma 桌面应用本地 MCP 服务访问完整功能，包括 Figma Make 设计生成、代码生成、设计系统管理等，无需 OAuth 认证

A comprehensive AI agent skill for navigating court systems and legal proceedings. Helps you understand what type of court handles your situation, prepares you for hearings, explains court documents i

豆包 AI 创作自动化 - 通过 CDP 浏览器自动化实现无手动交互的图像生成与提取。工作流：1) 连接已打开的豆包页面 2) 导航到 AI 创作页 3) 输入 prompt 并自动生成 4) 提取生成的图片 URL 5) 下载保存到本地。

Continuous behavioral monitoring for OpenClaw agents. Detect anomalies in command patterns, resource usage, and skill invocations against established baselines.