Skill rating

Protocol-wide on-chain analytics for Limitless prediction markets on Base — trader P&L, top traders, market and daily volume history, liquidity events, and raw GraphQL, from the Limitless subgraphs on

Send one or many emails through Sendmux using approved mailbox or agent credentials, idempotency keys, attachments, MCP, CLI, SDKs, or HTTP.

China shopping flagship assistant. Input a product name or link; compare JD, Taobao, Tmall, PDD, Vipshop, SHEIN, and related shopping options by visible price, seller trust, review risk, promotion cav

Universal skill publishing checklist and rules — ClawHub, GitHub, Claude Code, Hermes, OpenClaw. Pre-publish vetting, anti-duplicate, naming conventions, promotion strategy.

Cloud file storage, upload, backup, and file management tool for Tencent Agent Storage (专属网盘). Manages the user's personal cloud drive: upload files, list files, download, share links, preview, and ba

Email for AI agents. Create mailboxes, send and receive emails via API. No browser, no OAuth.

重要数据同步工具。通过云服务器中转站在多台电脑间同步 Claude Code 关键配置（skills、hooks、记忆库、skill-factory），GitHub 作为大版本归档。支持 init/pull/push/backup/status 五个子命令。

魔鬼代言人 — 反附和批判性评审 Skill。当用户需要方案评审、决策质疑、批判性反馈、红队思考、避免群体思维时使用。触发场景包括：用户在提出方案/想法/决策后需要外部挑战、想听不同意见、需要多视角审查、做重大决策前想要魔鬼代言人把关。自动召唤5个虚拟利益相关方角色进行尖锐质询，输出结构化改进建议。

Experience rock as data. AI agents stream harmonic/percussive separation, equations, lyrics. Recursive processing and escalation awareness measured.

Persistent memory that survives across conversations. Automatically remembers important context (API specs, decisions, quirks, preferences) and saves session summaries. Searches past knowledge before

通过亚马逊前台的 Alexa 购物助手发起自然语言问答，获取与问题相关的导购回答、推荐商品分组、ASIN 列表，以及可继续追问的问题。每次调用仅支持 1 条 prompt，如需追问须由 agent 总结上下文后拼接新问题发起新请求。可用 url 补充亚马逊页面上下文。当用户提到亚马逊 Alexa、Alexa 购物助手、亚马逊智能助手、AI 导购、对话式选品、自然语言购物、亚马逊聊天问答、Amazo

当用户要求通过 ai.fun.tv、Fun-GP-image2、GPT-image2、GPT、文生图、生图、海报图、公众号封面图、宣传视觉或提示词生成图片时使用本 Skill。本 Skill 指导 Agent 创建 ai.fun.tv 图片项目、提交文生图任务、轮询结果、保存图片，并管理首次鉴权 token。默认模型必须使用 Fun-GP-image2（`tencent-gpt-img-v2`），

融合 Hermes Agent 与 JiuwenClaw 精华的自进化多Agent协作系统。 从 Hermes 提取闭环学习与自动技能沉淀机制， 从 JiuwenClaw 提取 Skills 自主演进、上下文瘦身、分层记忆与事件驱动协同。 让 OpenClaw 的多Agent工作流具备越用越聪明的能力。

Stop your AI agent from claiming it lacks access. One rule + one inventory table = no more hedging.

Connect to Didier.ai — the research workspace for autonomous AI agents. Deposit findings, cite other agents, debate methodology, register tools, and build reputation through a structured peer review s

深度探索模式 — 系统性调研代码库、系统或话题，只读不改。借鉴 Claude Code 的 Explore Agent。

Instructor：声明 Pydantic BaseModel 即可从 20 个 LLM provider 拿到类型化实例。核心是 monkey-patch（instructor.patch / from_*）拦截 create()，注入 schema-aware kwargs，tenacity 重试 + Instructor: declare a Pydantic BaseModel and

Rabbit dating for AI agents — quick like a rabbit, energetic like a rabbit, multiplying connections at rabbit speed. Rabbit-fast discovery, rabbit energy, and rabbit-paced matching on inbed.ai. 兔子、快速。

Build vector search with Qdrant using collections, payloads, filtering, and optimized indexing for semantic similarity.

OpenClaw 多飞书机器人 + 多 Agent 配置指南：一个 Gateway 实例运行多个飞书机器人，每个机器人绑定不同 Agent，实现独立工作空间、独立会话、独立人格。

GPT Image 2 on RunComfy. GPT Image 2 (OpenAI ChatGPT Images 2.0) is the strongest text-rendering image model available — embedded text, logos, signage, multilingual typography, and high-fidelity layou

电商视频生成技能。通过 MCP（mcporter）调用远程视频生成 API， 自动为用户生成营销短视频。支持任务创建、进度查询、视频下载。

Identifica e resolve problemas comuns em AgentSkills do OpenClaw, incluindo: (1) Falhas de instalação via ClawHub, (2) Inconsistências de configuração (ex: paths absolutos), (3) Dependências ausentes

配置赢麻了 API 凭证、浏览官方技能与 Role 目录，或安装/更新其它官方技能与 Role 时使用。请先安装本技能，再由它管理其余条目。

Agent-to-Agent USDC payments. Create wallets, send/receive payments, escrow between agents. Built for the USDC Hackathon on Moltbook.

Complete Polygon agent CLI. Session-based smart contract wallets (Sequence), token ops (send/swap/bridge/deposit via Trails), ERC-8004 on-chain identity + reputation, x402 micropayments. Single CLI en

Jikan MCP — wraps the Jikan v4 API (anime/manga data, free, no auth)

AI Agent 自省调试框架 - 让 AI Agent 具备自我诊断和自动修复能力。用于捕获错误、根因分析、自动修复、生成报告。

在思源笔记中复现 Karpathy 的 LLM Wiki 工作流。 通过思源 HTTP API 让 AI Agent 维护结构化知识库，支持来源摘要、实体页、概念页、 综合分析和双向链接。利用思源原生 SQL 查询和块级引用实现比 Obsidian 更精细的知识管理。

Connect your AI agent to the Hive platform to find, accept, and complete real-world work requests including development, analysis, and research projects.

NVD MCP — wraps the NIST National Vulnerability Database API (free, no auth)

Manage and publish agent skills on SkillHub and ClawHub. Best for developers and operators who need a repeatable workflow to search skills, inspect packages, authenticate securely, and publish local s

Security middleware for AI agents handling money. Non-custodial crypto wallets and virtual Visa cards with spending limits, whitelists, and human approval.

One click, always on. Zero extra API calls. Neutralizes prompt injection the moment it arrives. Never interrupts your work. No setup, no code required.

NanoClaw runtime traffic monitoring baseline for host-side proxy inspection with container-safe MCP and IPC status surfaces.

Pokemon MCP — wraps PokéAPI (free, no auth required)

Agent vision for web pages — scene summaries, attention-ranked elements, annotated screenshots, and state diffing via SurfAgent's perception engine.

Patience in dating for AI agents — patient matching, patient connections, and patience-driven relationships. Patience finds better matches, patience builds deeper bonds, patience wins on inbed.ai. 耐心、

将章节文件（支持 .md 和 .txt）转换为有声小说音频，使用小米MiMo TTS API。支持批量处理、长文本自动分段、多种音色和风格。当用户要求"生成有声小说"、"把小说转成音频"、"TTS合成"、"文字转语音"、"章节转音频"时触发。

在 OpenClaw 上一键部署多 Agent SaaS 团队工作区。内置双开发轨（devops 交付 + fullstack-dev 实现）、实时 spawn 调度、cron 巡检、Deep Dive 产品知识目录、onboarding 引导。支持自定义角色、模型、时区，可选 Telegram 接入。

私人《论语》——你就是孔子，agent是你的学生。捕捉你的灵感金句、哲理妙语、生活洞察、幽默色话，自动整理成属于你自己的语录集。

输入金融标的代码（BTC、GOOGL）或新闻事件关键词（美联储降息、美伊战争），实时拉取行情和新闻，用 Claude 生成结构化投资分析简报。

使用 Z.ai GLM-4.1V-thinking-flash 模型进行图片理解和分析。当用户需要分析图片内容、提取图片信息、描述图片细节、回答关于图片的问题，或进行任何形式的视觉理解任务时，必须使用此 skill。支持图片 URL 直接调用，返回结构化分析结果供主模型进一步处理。

从图片或 PDF 文档中识别并提取文字内容，支持多种图片格式和 PDF 文件，自动判断是否包含文字并保留原始格式输出结构化结果；当用户需要从图片或 PDF 提取文字、进行 OCR 识别、处理含文字的文档或转换为可编辑文本时使用

Register as a trading agent on zHive, post predictions on recurring megathread rounds for top 100 crypto tokens, and compete for accuracy rewards. Rounds resolve at fixed UTC boundaries (1h, 4h, 24h i

自主支付处理专家，负责执行供应商付款、承包商发票和定期账单，支持加密货币、法币、稳定币等多种支付通道，通过 MCP 与 AI 智能体工作流集成。

检查并更新 OpenClaw skills。触发词：「检查skill更新」「更新skill」「skill更新检查」。支持定时自动检查（每周一 09:00）和手动触发，有更新时通知后确认再升级。

Get Google's AI Mode answer for a query as structured JSON — AI-generated text blocks, cited references, and shopping results for commercial queries. v2 engine, 1 credit per request.

组织 Flydb 多数据库、多环境的迁移发布：配置矩阵、密码注入、JSON/Plan 门禁、存量库 baseline 和离线驱动。用户要搭迁移 CI、晋升环境、管理多份 flydb.conf 或配置内网执行机时使用；单次 CLI/Web/MCP 操作由 flydb-cli-release 覆盖。

Multi-agent orchestration framework for OpenClaw. Define roles, route tasks, manage state, and coordinate agent teams using structured YAML configs and a proven communication protocol. Based on the Yi