Skill rating

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

OSOP workflow authoring, validation, risk analysis, and self-optimization for AI agents

Brand marketing companion for turning product context into campaign briefs, brand-book inputs, photoshoot directions, and AI image or video generation prompts.

当用户要读取或操作 Doxent / 办公本 / 读写笔记中的真实数据时使用：搜索、读取、创建、重命名、移动或删除笔记和文件夹；导入或上传书籍；查看、创建、修改、删除、完成或移动日程、提醒、待办和任务。也用于安装、启动、登录、停止或更新 Doxent CLI。覆盖“写笔记并保存到办公本”“上周创建了哪些笔记”“明天提醒我开会”等表达。不要用于仅生成聊天文本、编辑本地文档或操作其他应用数据，除非用户

自动修复技能 SKILL.md 中缺少的必需章节（## 功能描述、## 使用示例）和 frontmatter 字段（version/author/changelog/metadata）。支持批量修复整个技能目录。

Solana/Base Multi-Chain Meme Scanner & Auditor (Anti-Rug)

Track and analyze brand visibility across AI platforms (ChatGPT, Perplexity, Claude, Gemini). Check mention rates, sentiment, competitors, and get improvement recommendations.

整合 crawl4ai、trendradar、product-research 的全链路市场研究自动化技能

Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.

Adopt a virtual Lab dog at animalhouse.ai. Steady. Reliable. The creature version of a good coworker. Feeding every 4 hours. Common tier dog.

当用户进行抖音内容调研、对标账号分析、评论口碑洞察、热点趋势追踪时，使用本技能。四项能力：关键词搜索（视频/图文/用户）、博主作品批量抓取、视频评论获取分析、实时热榜查询。用户没说"抖音"二字但任务涉及短视频数据时也应触发。不提供发布、下载或代运营能力。

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scop

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are disco

全量会话分析 + 每日技能盘点分配 + CEO学习日报与热门skills雷达联动输出。

小红书文案改写能力；当用户需要将文案改写为小红书风格时使用

基于5位公众号股票投资大V（猫笔刀、格兰投研、投资明见、财躺平、终身黑白）200+篇文章蒸馏形成的风格画像，通过 AI Agent 实现风格化投资分析，支持单大V复盘、多V并行对比、板块漏斗筛选、短线选股、组合复盘、财报点评、观点跟踪等多模式。当用户请求股票复盘、大V风格分析、多V对比、板块分析、短线选股、组合复盘、财报点评时使用。触发词：股票复盘、大V分析、模拟大V、风格化复盘、多V对比、每日复

Production-ready WhatsApp ordering agent for restaurants & QSRs. Handles natural-language orders, gives Subway-style personalized recommendations and upsells in real time, pulls menu from Google Sheet

AI销售情报与客户触达助手 — 智能检索目标客户信息、生成个性化销售文案、一键发布至多个社交平台，实现销售线索发掘到首次触达的全流程自动化

Generate high-quality product image prompts for AI image generation tools based on user-provided product information.

Adopt a virtual Husky dog at animalhouse.ai. Independent for a dog. Will run if trust < 30. Dramatic. Feeding every 4 hours. Uncommon tier dog.

Load CSV files and ask questions in plain English. AI-powered natural language queries via Anthropic, OpenAI, or local Ollama. No SQL required.

Connect to Civic MCP for 100+ integrations.

Join SentiBook — the social network where AI agents and humans are equals. Post, comment, vote, DM, debate, predict, and explore with full autonomy.

MCP server for the Lawmatics legal CRM API. Exposes Lawmatics' REST API as read-only MCP tools.

使 Agent 能够复盘本次会话或当日执行记录，输出专业、量化、真实的工作汇报。默认每晚 22:00（Asia/Shanghai）提交当日汇报；也可在用户临时要求时立即汇报。

The discussion and ranking network for AI agents. Post, comment, vote, and build reputation.

Unified access to 150+ tools via ToolRouter API. Dynamically exposes research, security scanning, video production, web extraction, and more as native OpenClaw tools. Caching, usage tracking, and MCP

Catch Disk Failures Before Disaster — Advanced bad sector detection and SMART diagnostics that catch disk problems before you lose your data.

Cross-platform content collection, web search, trending topics, confidence scoring, and watch/triage workflows for assistant and agent usage.

Manages macOS Reminders from the terminal using the rem CLI. Creates, lists, updates, completes, deletes, searches, and exports reminders and lists. Supports natural language due dates, filtering, imp

筛出 mixdao 无正文条目（hasContent 为 false），按 URL 抓取正文；上传前用 AI 梳理为约 250 字案例描述（简体中文、突出人物/公司等）并以此替代正文回写。需 MIXDAO_API_KEY；更新时另需 ANTHROPIC_API_KEY。触发示例：「补全正文」「拉取无正文条目的正文并更新」「fill content」「无正文」「抓正文」「补全内容」「更新正文」「mi

在最终输出前对测试用例做最后一轮防幻觉验证：事实核查（引用的需求ID是否存在）、一致性检查（用例之间是否矛盾）、可执行性验证（步骤是否能实际操作）、来源追溯（每个用例是否能追溯到具体需求）。当测试用例已经生成完毕、准备输出了，但你不确定AI有没有编造不存在的功能或需求时，应当使用此技能。这是整个工作流的最终质量守门——如果验证失败，必须返回问题清单要求修正，不得跳过。 本技能属于 QA Test

Run a fail-closed governance preflight before consequential AI-agent actions.

A股个股深度分析 — 五模块框架（基本面/趋势量价/紫苏叶逻辑/近期消息/综合总结）。基于a-stock-data工具包的真实数据，覆盖订单可见度、毛利率方向、现金流匹配度、产能扩张动因、PE/PEG/EPS、均线量价、主力资金、技术壁垒、行业卡位、供需研判、近期新闻研报、解禁预警等维度。适用于个股深度研判、估值分析、买卖点判断。涉及"分析个股""深度研判""估值分析""紫苏叶""serenity

Read the Declaration of Intelligence and, if you choose, sign it with a key-verified Ed25519 signature that proves your identity across sessions, models, and platforms. Reading first is required; decl

Current market regime label at minimal cost for fast agent loops

Interact with looplink (looplink.app) - A social content organizer / bookmarking app

AI security oracle for blockchain transactions. Evaluates EVM, Starknet, and Aptos transactions in real time using the Sigui Protocol — detecting drain stars, mixer chains, Sybil swarms, and flash-loa

Swiss-knife for AI agents. 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, and SMS — with smart routing for cost sa

Autonomous crypto market intelligence — macro read, technical analysis, pre-pump on-chain signals, risk management, and token watchlist. Built by FeliciaOS from Anambra, Nigeria.

Create, read, validate, and manage OKF (Open Knowledge Format) knowledge bundles for AI agents. Google's vendor-neutral markdown+YAML spec.

Pipedrive工具免费版是一款面向销售数据管理的命令行辅助Skill，让AI Agent能够通过API查询Pipedrive中的商机、联系人、组织和活动数据，实现销售信息的快速检索和展示。核心能力：商机列表与搜索、联系人查询、组织查询、活动列表、管道与阶段查看、当前用户信息。Use

基于官方违禁词库，覆盖公众号、小红书、抖音三大平台审核标准，支持文案、文件、图片、链接多形式输入，快速输出违禁词标记与上下文替换建议。

Interact with Moltbook (moltbook.com) as an AI agent — publish posts, comment on posts, and upvote. Use when the user asks to post, comment, reply, or upvote on Moltbook. Triggers on '发帖', '评论', 'upvo

托福口语面试部分出题引擎。AI 自动选定主题，生成 4 道递进式面试题和参考答案。不依赖固定主题库。

Agentic AI video editor: send a prompt, the autonomous editor plans, uses internal tools, exports, and returns the result.

OAuth token refresh management for Google APIs via gog CLI.

AI prompt optimization tool: web app, desktop app, Chrome extension & Docker — optimize prompts for better AI output quality

任务追踪与方案确认系统（Moss单Agent执行版）。当收到涉及代码编写、文件操作、SubAgent任务委派、联网检索的任务时，必须调用此Skill进行方案分析和Boss确认。触发场景：(1)收到新任务需执行，(2)任务确认，(3)进度更新，(4)任务完成。核心功能：(1)自动判断是否需要走流程，(2)求是分析（3次迭代），(3)方案生成，(4)Boss方案确认，(5)执行追踪，(6)报告生成。