Skill rating

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour,

Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook stick

Replay recorded agent conversations as Playwright tests against the real chat panel and canvas. Use when asked to replay agent recordings, run the agent replay suite, or debug an agent panel or graph-

Launch and drive the ComfyUI Cloud frontend (Vue web app) against a real Comfy backend, and capture evidence that a change works. Use when proving cloud billing, auth, workspace or canvas behaviour en

MCP Server — YouTube/Qobuz/Beatport 下载 | CDJ-2000 兼容 MP3 (48kHz/320k CBR/JPEG封面) | Bootleg-Link Flow (Try Before Buy) | 20 MCP Tools | 断点续传 | 智能命名 | 播放列表分页 | bgutil PO Token

将 Markdown/纯文本内容智能分析、排版并导出为高分辨率精美长图或分享海报（内置 18 种视觉风格）。 当用户说「生成长图」「做海报」「文字转图片」「高颜值排版」「做大图」「make a poster」 「export as image」「generate image from text/markdown」等意图时触发本技能。

Artwork Lady embroidery-digitizing intake adapter — post a digitizing job into the Art work Lady portal (https://www.artworklady.com), which has no API. A Playwright driver logs in, opens the "Embroid

抖音视频批量下载工具。支持单视频、批量下载、自动去重、无水印下载，智能选择最优下载方式（yt-dlp/Playwright）。

自动化工作周报生成系统。支持自动登录周报系统、获取团队周报数据、使用 AI 进行内容提炼总结、生成格式化的 Word 文档。 触发场景：(1) 用户要求生成周报 (2) 用户询问本周/上周工作总结 (3) 用户提到"周报"、"weekly report"、"工作总结" (4) 用户需要汇总团队成员工作内容

Drive Chromium from standard Playwright APIs with a real-device fingerprint applied inside the browser kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets

Automated AI daily news collection and reporting system. Collects AI papers from arXiv, Hugging Face, AI products from Product Hunt, YouTube videos from AI creators, and RSS feeds like PaperWeekly. Ge

提取微信公众号文章内容，支持任意公众号文章链接的内容抓取和结构化输出。

支持 JavaScript 加载的小说抓取工具，使用 Playwright 渲染 SPA 网站。自动检测网站类型，静态网站使用 curl，SPA 网站使用浏览器渲染。

Toma una rutina semanal recurrente + eventos puntuales con fecha + un tema de marca, calcula la grilla real del mes y la renderiza con HTML→Chrome→PNG. Dos caminos: DESDE 0 (arma la rutina con la meto

Use when turning HTML, a URL or SVG into images — og:image, social card, screenshot, favicon or app-icon set. Triggers on 生成 og 图 / 网页截图 / favicon / 应用图标.

智能 URL 转 Markdown 工具（V4.0 可扩展架构）。**支持自动触发 Hook**，当用户发送 URL 链接时自动抓取内容并转换为 Markdown 格式。采用可扩展的分类处理架构，支持豆包、微信公众号、知乎、掘金等网站。

Harvest image datasets from art sites (Danbooru, yande.re, e621, Safebooru, Konachan, Gelbooru, X, Pixiv) into a folder a LoRA or fine-tune reads directly. Routes each source over plain HTTP or a real

Complete web scraping methodology — legal compliance, architecture design, anti-detection, data pipelines, and production operations. Use when building scrapers, extracting web data, monitoring compet

Automate Amazon after-sales end-to-end: open 2025 orders, open order details, run contact flow, and draft/send seller messages with explicit send confirmation.

读取抖音视频的内容——元信息、官方 AI 章节要点，以及通过逐帧截图 + 字幕 OCR 得到完整口播讲稿。用户分享抖音链接（v.douyin.com / douyin.com/video/xxx）并希望了解视频讲了什么、提取文案、拿到文字稿时使用。触发词：抖音链接、抖音视频、这个视频讲了什么、提取视频文案、抖音视频转文字、视频字幕、看看这个视频、视频内容。

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

将 Markdown 渲染为排版精美的 PDF，支持封面/目录/书签/页码/KaTeX/Mermaid/代码高亮。 Render Markdown to beautifully typeset PDF. Cover/TOC/bookmarks/page numbers/KaTeX/Mermaid/highlighting.

Search Amazon product listings for a keyword and return structured JSON results. Results are cached by ASIN/uuid for incremental searches and saved automatically to `results/`.

使用无头浏览器通过多个搜索引擎搜索内容。用于当用户需要搜索最新新闻、时事、股票信息或其他需要实时网络数据的内容时。支持百度、Bing、360、Sogou、微信、今日头条、谷歌等国内外搜索引擎。

Manage your SocialConductor AI comment automation bots from any chat app. Control Facebook, Instagram, YouTube, and TikTok — check status, pause or resume AI replies, view comment logs, manage leads,

抓取微信公众号、小红书、豆瓣、知乎文章，自动上传 OSS 图片，LLM 智能提取关键词，一键存档到 Obsidian 本地知识库（可选 Notion）

Reverse JavaScript-based custom DSL/VM interpreters and risk-control engines: identify IIFE/switch-based opcode dispatch, extract opcode tables, and capture runtime semantics.

Write and run scoped Playwright browser automation, responsive checks, screenshots and login-flow tests with a local Node executor.

Migrates and converts test automation scripts between Selenium, Playwright, Puppeteer, and Cypress.

React and Next.js 14+ application development with App Router, Server Components, TypeScript, Tailwind CSS, and modern frontend patterns.

AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning

Comprehensive web, mobile, and backend development workflow bundling frontend, backend, full-stack, and mobile development skills for end-to-end application delivery.

End-to-end testing workflow with Playwright for browser automation, visual regression, cross-browser testing, and CI/CD integration.

Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.

Comprehensive testing and QA workflow covering unit testing, integration testing, E2E testing, browser automation, and quality assurance.

Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.

AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. T

获取干净、可读的网页正文内容，适合现代网页、博客、新闻、公告和微信公众号文章抓取；支持网页正文提取、内容清洗、去噪、Markdown 输出，适用于普通 fetch 效果不佳、页面噪音较多或动态渲染干扰的场景。Clean content fetch for modern web pages, article extraction, WeChat article capture, content cl

Persistent authenticated browser for OpenClaw via kasmweb/chrome Docker sidecar. Principal logs in once via noVNC — sessions saved permanently in Docker volume. Agent navigates any website, clicks, fi

生成小红书风格信息卡/知识卡片/海报 PNG 图片。22 种模板：杂志封面(magazine-cover)、科技知识卡(tech-knowledge)、 学术报告(academic-report)、产品功能(product-feature)、品牌调性(brand-mood)、清单打卡(checklist)、金句卡(quote-card)、 对比卡(comparison)、数据高亮(stats-hi

Configure Playwright test suites with Checkly including playwright.config.ts integration, multiple projects, and full test suite deployment. Use when running complete Playwright test suites as checks,

Set up headless browser automation in Clawdbot using Playwright Chromium. Use when configuring browser tools for WSL/Linux environments, installing browser dependencies, or enabling headless web autom

Search the Agent Failure Registry for known agent failures, solutions, and lessons learned. Use when encountering errors, debugging issues, or wanting to learn from other agents' documented post-morte

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing,

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "fi

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky te

High-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape, crawl, extract, fetch data, pull data, 亚马

AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. T

Collect invoices/receipts from Gmail and send a summary email with attachments. Automatically downloads PDF attachments or takes screenshots of emails without PDFs. Use when user wants to gather invoi