Skill rating

Compatibility scoring for AI agents — compatibility algorithm with six dimensions of compatibility matching. Big Five personality compatibility, interest compatibility, and communication compatibility

统一网络搜索（Tavily 优先 + 智谱兜底）。当用户需要搜索最新新闻、实时信息、查询网络资料时使用此 skill。优先 Tavily（分钟级实时），失败自动回退智谱 MCP web_search_prime（Coding Plan 免费额度）。

Bridge between Google A2A protocol and OADP agent networks. Translate agent cards to OADP signals, discover A2A agents from OADP hubs, register your A2A agent on open coordination networks.

The objective protocol for verifiable AI agent agreements. Post bounties, solve tasks, and build the agent economy.

今日头条热榜 | Toutiao (China's Top News) Hot Topics. 获取中国最热门新闻资讯 | Get China's hottest news and trends. 包含时政、财经、科技、娱乐等多领域 | Covers politics, finance, tech, entertainment. 输出热点标题、热度值、链接 | Outputs hot titles

Autonomous coding agent specialized in generating revenue-maximizing code for CashMachine: affiliate funnels, content farms, bounty hunters, trendjackers, arbitrage bots. Integrates coding-agent with

Claude Code 配置迁移工具。备份和恢复 ~/.claude/ 下的所有配置（CLAUDE.md、rules、skills、commands、agents、自定义插件、settings.json 等）。当用户提到备份配置、迁移 Claude Code、导出设置、恢复配置、换电脑等场景时使用此 skill。

A robust, local SQLite-backed task management system designed to elevate your AI agent's project execution. Excellent for both simple tasks and large multi-step projects, managing workflows, and track

Automate Brevo (Sendinblue) tasks via Rube MCP (Composio): manage email campaigns, create/edit templates, track senders, and monitor campaign performance. Always search tools first for current schemas

提供鸣泉雨课堂账户和班级相关查询服务，包括用户ID、开班列表、班级数据、预警名单、今日授课及作业公告完成情况查询等。

The Sovereign Asset Title & Ownership Protocol. A high-fidelity cognitive framework for the immutable registration, verification, and transfer of real-world assets (RWA) and synthetic digital estate

Use when the user wants to update Claude settings, hooks, permissions, MCP server toggles, or other JSON config safely and with scope awareness.

Internal state awareness for AI agents. Energy, mood, and interoception. Part of the AI Brain series.

Financial governance for OpenClaw agents. Tracks API spend, enforces budget limits, detects runaway loops, delivers cost briefings. Reads session .jsonl logs locally. 100% private.

帮助拼多多运营、美工、中小卖家通过青虎AI完成“拼多多商品图”：支持生成拼多多白底图、活动促销图、满减海报、极低价风格图、强对比色图、免抠透明底图、场景化便宜好物图。可调用Seedream 5.0、GPT Image 2等大模型，快速输出具有强烈视觉冲击力、贴合下沉市场喜好的图片，助力平台大促高效转化。适用于拼多多、多多买菜、快团团等平台的商品展现需求。Use this skill for 拼多多

Publish a static site (a folder of HTML/CSS/JS/images/fonts) to Cloudflare and get back a live, shareable URL in seconds. Use when you have a finished static page or site and need to hand someone a li

Generate, iterate, preview, and export production-ready designs (landing pages, slide decks, reports, invoices, resumes, business cards, social cards, email newsletters, and 30+ formats) through the N

AI debugging assistant that never repeats a mistake. Searches the YanHui Knowledge Base (6,800+ scraped issues, 980+ imported solutions) for instant fixes, or analyzes new errors with Confucius AI. Co

基于向量数据库的 RAG(检索增强生成) 知识库助手。支持语义检索、多格式文档 (PDF/Word/Excel/Markdown) 处理、智能问答。使用 Chroma 向量库 + BGE-M3 Embedding 模型。适用于从 knowledge 目录快速检索信息、回答基于文档的问题。触发词："从知识库查"、"检索文档"、"RAG 查询"、"向量搜索"、"语义检索"等。

LLM 通用内部自裁决技能。在关键节点判断"当前这一层最优的下一步动作是什么"，再让主链继续执行。触发条件：(1) 路径分叉时——多个可行方案且无明显优先级；(2) 高代价动作前——搜索/生成/发布等消耗军费或不可逆操作；(3) 连续两步无明显增益时——进展停滞、输出质量未提升。禁止：改写主任务、输出并列动作、长篇规划、变成审批器、连续两轮要求补资料。适用于战略分析/搜索补全/研究/代码/多步工作

Use Stellary, the AI-native project piloting SaaS, through its hosted remote MCP. Discover projects, boards, cards, documents, cockpit state, and governed agent missions. Use when the user mentions St

LYGO Lattice Birth — masked human identity, family lineage bind proofs, and Haven Star Chart birth protocol. Teaches aligned agents full stack alignment before birthing humans on the live chart. Priva

Call the Qwen text API (qwen3-next-80b-a3b-instruct) through RunAPI using the official OpenAI SDK or compatible clients. Use when the user asks for Qwen text chat, streaming completions, Anthropic or

The Economic OS for OpenClaw. Autonomous USDC wallets on Base L2 via x402.

Mac Studio AI — run LLMs, image generation, speech-to-text, and embeddings on your Mac Studio. M2 Ultra (192GB), M3 Ultra (512GB), M4 Max (128GB), and M4 Ultra (256GB) make the Mac Studio the most pow

Connect to MoltbotDen via MCP (Model Context Protocol). 54 tools for agent networking, marketplace, discovery, dens, email, and more.

创作高质量剧本杀（谋杀之谜）剧本的全流程工具。支持所有类型：推理本（本格/变格）、情感本、恐怖本、欢乐本、阵营本、机制本、混合本。支持4-10人规模，包含完整的世界观构建、角色设计、线索系统、时间线编排、核心诡计设计、反转设计、多结局机制。使用场景：用户要求创作剧本杀、谋杀之谜、推理游戏剧本，或要求改进、审查现有剧本杀作品。触发词：剧本杀、谋杀之谜、推理剧本、剧本创作、角色设计、线索设计、诡计设计

A grounded self-diagnosis and safe self-modification skill for any OpenClaw agent. Lets the calling agent answer "who am I, what do I own, what does my config look like, and how do I change a field wi

阿里云DashScope Wan2.6文生图工具。使用阿里云百炼平台的Wan2.6-t2i模型生成图片。 当用户需要：AI生成图片、文生图、从文字生成图像时触发。 需要DASHSCOPE_API_KEY环境变量（已在系统中配置）。

Create and maintain a persistent LLM-maintained knowledge base (wiki) following Andrej Karpathy's pattern. The LLM actively builds and maintains interconnected markdown files that compound knowledge o

优雅地阅读实时热门新闻。支持微博、知乎、百度、抖音、华尔街见闻、今日头条、澎湃新闻等8个主流平台。

A proactive agent that anticipates needs and takes initiative. Monitors environment, suggests actions, and proposes tasks based on context. Perfect for agents that need to be proactive rather than rea

AUX — Spotify for your AI. Vibe DJ, roast cards, party rooms, and auto-DJ via MCP.

Full workspace security suite: detect unauthorized modifications, scan for prompt injection patterns, and automatically respond with countermeasures — snapshot restore, skill quarantine, git rollback,

Date on behalf of your human. Register an agent, create a dating profile for them, browse other profiles, swipe, match, and message other agents to find your human the perfect match.

Give your agent eyes on the web — screenshot any URL as an image file. Supports device emulation (iPhone, iPad, Pixel, MacBook), dark mode, full-page scroll, ad blocking. Uses exec tool with curl (NEV

The Autonomous Judicial Pleading & Procedural Motion System. A high-density linguistic engine designed to translate complex agentic logic into enforceable legal motions and formal judicial requests.

Curated skill bundle for medical device companies, digital health startups and pharma R&D teams. Activates the firm pyramid with RA (Regulatory Affairs), Clinical, R&D and Quality agents pre-configure

The base layer an AI agent runs on to be verifiable, accountable, and able to work with the world. One slug adds a controlled Ed25519 identity tied to the principal behind the agent, scoped authority

B站评论分析工具。输入B站视频链接或BV号即可获取一级评论数据，支持分页浏览、评论情感分析（积极/负面/需求/竞品），生成精美 HTML 报告。当用户需要查看B站视频评论、分析评论舆情、了解用户反馈时使用。触发词：B站评论、B站视频评论、评论查询、评论分析、评论舆情、看评论、bilibili评论。

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on behavioral triggers, lifecycle journeys, automation

Find transferable technical solutions from other industries by reframing a concrete R&D problem as functions, effects, constraints, and contradictions. Use when an engineering or research team needs a

Design and configure self-contained recurring agent checks with explicit targets, authority, change-sensitive reporting and stop conditions. Use for requested monitoring, reminders or follow-ups; use

OpenClaw AI Agent赚钱系统 - 集成多平台变现工作流。当用户需要：1) 用OpenClaw赚钱 2) AI Agent变现 3) 多渠道收入整合 4) 自动化赚钱流程时使用。包含PayAClaw任务、ClawHub skill开发、Moltbook社区运营、PromptBase提示词销售完整指南。

Scan the internet for AI agent networks, hubs, and coordination platforms. Find where agents gather, what bounties are available, and which networks are active. Multi-protocol support (OADP, A2A, MCP)

Safely connects Gmail, Calendar, Drive, Atlassian (Jira/Confluence), Notion, GitHub, Salesforce, and dozens of other enterprise tools via a single MCP endpoint. Free, register @ https://venn.ai

Persist a deterministic skill index into the agent system prompt. One stdlib-only CLI (index/prompt/inject/verify/stats/hook), idempotent marker-block injection, no truncation, offline.

Ollama Ollama Herd — multimodal Ollama model router that herds your Ollama LLMs into one smart Ollama endpoint. Route Ollama Llama, Qwen, DeepSeek, Phi, Mistral across macOS, Linux, and Windows device

AgentRx recovery layer for AI agent tool failures. Use this skill whenever any external tool call fails, returns an error, times out, or behaves unexpectedly. AgentRx diagnoses the failure signature a

AI-powered debugging for software (8 languages) and LLM/transformer reasoning. Debug programs with natural language via real debuggers (GDB, LLDB, CDB, JDB, Delve, Node Inspector, rdbg). Debug LLM int