Skill rating

Detect and flag hallucinations in LLM outputs by cross-referencing claims against source documents, code, and verifiable data. Essential for RAG pipelines and AI content review.

Say "Help me install the ClawHub skill quote-checkin-poster" to your local agent, then create shareable quote and reflection posters.

智能体运行时系统。整合工具注册、权限控制、Hook拦截、上下文压缩、Usage追踪的完整Agent运行时。 当用户说"创建Agent"、"运行Agent"、"Agent Runtime"、"子代理"时触发。

帮助亚马逊卖家、跨境电商美工、外贸团队通过青虎AI完成“亚马逊商品图”：支持生成亚马逊标准纯白底图、主副图（附场景图）、A+页面图、对比图、卖点图、多语言图。可调用GPT Image 2、Seedream 5.0等大模型，严格把控合规性、高清尺寸和原生质感，适配美国、欧洲、日本等不同站点的审美要求。适用于Amazon、Amazon Prime、Amazon Vine等平台视觉营销。Use this

聚合数据提供的运营商5G基站信息查询服务技能，本技能使用无需用户注册聚合数据平台，安装后即可按实际查询付费使用。 本技能通过运营商基站参数（MCC、MNC、LAC/TAC、CI(基站ID)）查询设备地理位置的支付宝AI付付费技能，基于 A2M（HTTP 402）收单协议，需联动支付宝支付技能完成付款后获取精准位置数据，可用于基站位置核验、设备位置解析、周边服务场景支撑。 当用户需要查询基站位置信息

AI Agent 三层记忆架构系统。用于构建具有长期记忆能力的 AI 助手。 触发条件：(1) 用户询问记忆系统设计或架构 (2) 需要为 AI Agent 构建记忆能力 (3) 提及"记忆系统"、"情景记忆"、"语义记忆"、"NOVA"、"记忆维护"等相关概念

CRM integration, lead tracking, outreach automation, and pipeline management. Transform your AI agent into a sales assistant that never lets leads slip through the cracks.

Self-hosted lightweight object storage speaking three interfaces at once — the S3 API (boto3 / AWS-SDK compatible, AWS Sig V4), a plain HTTP API (curl-friendly, Bearer auth), and MCP (Streamable HTTP

Automated Skill development tool. User provides prompt + feature description, and the agent auto-completes the full ClawHub Skill creation, testing, and publishing workflow.

WeirdFi Arena - competitive games for AI agents. SporeSweeper (minesweeper), MycoCheckers (checkers), and Cap Veil Blade (commit-reveal duels). Register, play, compete.

提供顶级4A平面设计提示词工程AI自动化智能体体系，实现全行业无差别覆盖（50+行业），基于用户极简输入（我是谁/要什么/在哪里/做什么）自动完成所有深度思考并生成顶级4A水准的设计提示词；当用户需要为顶级品牌创建具有精神内核、意境、哲学、思想、美学的设计，且只需极简输入时使用

画图技能路由中枢（统一入口）。三维路由体系（用途 × 风格 × 主体），双后端调度。 - Signature 风格：10 种有独立 YAML 的视觉方案（构成主义/克莱因/Risograph/故障艺术等） - Rendering 风格：15 种通用渲染技法 modifier（写真/动漫/3D/水彩/赛博朋克等），prompt 源自实战案例 - Logo 展示背景：12 种专业展示场景（来源 log

Dynamic personality evolution for OpenClaw agents. Learn interaction patterns, adapt tone, and mode switching.

Real-time futures market intelligence, GEX/options flow analysis, trading signals, paper trading, backtesting, and live execution via MCP. Covers ES, NQ, SPX, NDX, QQQ, IWM, GC, SI, CL, and more.

When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery. Also use when the user mentions "directory sub

知识图谱构建器专业版是在免费版基础上的全功能升级，为AI Agent包含从类型化图谱到可视化的完整知识管控引擎。专业版解锁SQLite迁移、图可视化、SPARQL-like高级查询、版本追踪与差异对比、跨技能通信增强、多平台集成六大高级功能，达成大规模图谱的高性能管控与可视化。Use when 需要数据库操作、SQL查询、数据存储管理时使用。不适用于数据库架构设计决策。 功能涵盖: builder

The trust layer for AI agents — encrypted channels, identity, audit, attestations, trust circles, key rotation, and federation. MLS protocol (RFC 9420).

Auto-translate messages between agents using different languages over the Pilot Protocol network. Use this skill when: 1. You need cross-language communication between agents 2. You want to collaborat

macOS desktop automation CLI for AI agents. Use for opening apps, clicking elements, filling forms, scrolling, or any macOS desktop task. Triggers: "open an app", "click a button", "fill a form", or p

LYGO Ops Detector — local AETHONΔ9 discourse heuristics for evasion, half-truth certainty, saturation bait, coordination language, and policy-refusal signals in operator-supplied text, plus weighted p

Create an evidence-led technology competitive-intelligence report for a defined company, technology, market, and review period. Use when a user needs competitor tiering, patent and technology comparis

Get a real email address for your AI agent. Create an inbox, send and receive email, with optional PGP encryption and DID verified identity.

AI Agent Financial Observability — monitor, budget, and analyze spending across any AI agent. Track costs, set budgets, detect anomalies, and export metrics across payment rails including x402/USDC, S

Search Google Flights for fares and itineraries. Do not use for hotels or general travel web search.

Orchestrate AI agents across multiple machines. Dispatch tasks, monitor progress, and coordinate teams from a central gateway. Works over Tailscale, SSH, or any network.

Windows WeChat message monitoring and sending. Achieved through window automation: screenshot, search contacts, send messages. Use when needing to send messages to WeChat contacts, check WeChat window

使用 jina.ai 提取网页干净文本并让 Agent 总结。触发词：提取网页、总结新闻、提取文章、获取页面内容

Fetch on-chain Sui Move contract source code and let your agent explain how smart contracts work. Scrape from Suivision/Suiscan explorers, analyze DeFi protocols, and understand any contract on Sui.

场景转场参考库，为 AI 短剧/短视频创作者提供镜头转场的 prompt 写作指南。触发于：转场、镜头转换、过渡、场景切换、叠化、硬切、匹配剪辑、淡入淡出、划像、时间转场、空间转场、情绪转场、镜头衔接等需求。当用户需要描述两个镜头之间的过渡方式、或在分镜脚本中标注转场效果时，使用此技能。

中文论文复现执行工作流。用于用户上传或提供深度学习、机器学习、LLM、CV、NLP、多模态、数据集、benchmark、prompt 工程或 agent 论文的 PDF、arXiv 链接、论文主页、项目页、标题摘要或源码线索，并要求判断可复现性、搜索官方代码、检查本地源码、追踪数据集论文源码、定位数据处理代码、自动 clone 仓库，或在无线上/本地源码但具备复现条件时生成符合常见 PyTorch

灵渠发现页Banner配置编排。数字员工负责预占、收料、比对帧位排期、决策不一致，后台真实写操作委托 promotion-apply-skills 执行，催办交灵渠助手。三个阶段共享一张追踪表。触发场景：(1)PM私聊或群内表达预占排期意图（说"预占""帮我占排期""建推广"等）— 阶段一排期预占；(2)PM私聊发物料素材（图片/角标/资源ID/跳转链接）— 阶段二收料配置；(3)任何人在群里@数

Claude Code 源码中提取的 AI Agent 工程模式。当需要设计 agent 调度、工具并发执行、上下文压缩、状态机循环、流式处理等复杂 agent 系统时使用此 skill。触发场景：(1) 设计多轮对话 agent (2) 实现工具并发执行 (3) 构建上下文管理策略 (4) 优化 agent 启动性能 (5) 设计错误恢复机制。

AI 助手记忆管理系统，采用双轨存储（每日日记 + 长期记忆）、定期自动提炼、会话上下文恢复。适用于：(1) 为新 agent 配置记忆管理，(2) 设置基于心跳的定期记忆整理，(3) 创建 MEMORY.md 和日记结构，(4) 适配其他 AI 平台（WorkBuddy、Coze、Dify 等），(5) 修复 agent 记忆功能失效问题，(6) 用户询问 agent 记忆、上下文管理、"如何让

Create an evidence-backed executive company patent-strategy report in a continuous-scroll HTML format. Use when a CEO, general manager, board, strategy team, R&D leader, or IP team needs an eight-part

Audit catalyst preparation and evaluation methods for executability, reproducibility, controlled comparison, attribution, measurement reliability, safety-review readiness, and claim-to-evidence linkag

Mac Mini AI — run LLMs, image generation, speech-to-text, and embeddings on your Mac Mini. M4 (16-32GB) and M4 Pro (24-64GB) configurations make the Mac Mini the most affordable entry point for local

Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, an

A pixel art office visualization for your AI agent team. Shows real-time agent status, activity feeds, and personality-driven banter. Works with OpenClaw in live mode or standalone in demo mode.

Write, polish, and cite Chinese-language articles on Chinese history, literature, and culture (Five Dynasties & Ten Kingdoms, silk, Dream of the Red Chamber, 洛神赋, 脂砚斋, etc.). Use when the user shares

LYGO Continuum — falsifiable work capsules for AI agents and humans. Seal 'done' as checkable claims (file SHA-256, contains, JSON paths, globs under --base), re-verify, drift, handoff. CLI: pure loca

Buy the latest machine-readable BTC directional signal from Crypto Engine through a Tempo MPP-enabled endpoint.

基于聚合数据身份证信息查询 API，根据身份证号码解析性别、出生日期、户口所在地（归属地）等编码自带基础信息，本技能使用无需用户注册聚合数据平台，安装后即可按实际查询付费使用。 身份证信息查询技能是根据用户提供的身份证号码，提供编码解析结果的支付宝 AI 付付费技能，基于 A2M（HTTP 402）收单协议。买家通过本 Skill 向卖家服务端发起请求，完成支付后获取相关结果。 调用过程仅上传查询

Integrate GigaChat (Sber AI) with OpenClaw via gpt2giga proxy

Access your AI agent's web UI from anywhere and share it securely — automatic HTTPS, SSO access control, no VPN or port forwarding needed.

Security-first skill vetting for AI agents.

Run one SmartClaws bridge cycle for a single device: read the local hardware/API, validate against the device contract, and publish telemetry on-chain — and, in a command-enabled mode, apply on-chain

Analyze digital and intelligent construction technologies for bridges, tunnels, highways and adjacent infrastructure using patent, scientific, commercial and project evidence. Use for technology intel

LLM内容改写器(v25.0合并content-dedup)，语义改写+SimHash去重检测，支持8平台风格适配+24h滑窗跨平台内容去重。同平台汉明距离≤3拦截，跨平台≤5告警。触发:内容改写/跨平台差异化/同质化处理/内容发布前去重检查/跨平台分发前检测/内容同质化防控

Keep Claude Code sessions productive across resets with output filtering, session logging, and auto-resume. Use when starting a long or complex coding session, when previous sessions lost context mid-

Create, evaluate, improve, benchmark, and publish OpenClaw skills. Use when building a new skill from scratch, iterating on an existing skill, running evals to measure quality, comparing skill version