Loading...
Loading...
Found 482 Skills
Analyzes Figma designs and generates implementation-ready PRDs with detailed visual specifications. Use when user provides Figma link or uploads design screenshots. Requires Figma MCP server connection.
Extract comprehensive JSON design specifications from visual sources including Figma exports, UI mockups, screenshots, or live website captures. Produces W3C DTCG-compliant output with component trees, suitable for code generation, design documentation, and developer handoff.
Browser automation for web tasks - scraping, form filling, testing, screenshots, data extraction. Use when tasks involve web pages, URLs, login flows, or web interaction.
Web UI testing and browser automation with Vercel agent-browser. Use when tasks require opening pages, interacting with forms, validating UI flows, taking screenshots, extracting page data, or running repeatable browser-based checks locally or in CI.
Extract text from images using OCR. Use when the user needs to read text from screenshots, photos, or image files.
Automates browser interactions using AgentGo's distributed cloud browser cluster via playwright@1.51.0. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information — running on AgentGo's remote cloud browsers instead of a local browser.
Run headless Chrome in Next.js serverless functions using @sparticuz/chromium + puppeteer-core. Use when the user needs browser automation from a Next.js app, wants to take screenshots or snapshots from server actions or API routes, or is building a Next.js app that needs headless Chrome. Triggers include "screenshot from Next.js", "headless Chrome in serverless", "browser automation in Next.js", "puppeteer on Vercel", or any task requiring Chrome in a Next.js server context.
Use for browser automation through camoufox-browser: open a page, inspect it with snapshot refs, click, fill, select, upload, take screenshots, and drive websites through the CLI instead of direct browser code.
Edit and design the materials provided by users (webpage URLs / PDFs / DOCX files / Markdown / plain text / screenshots / pasted content) into a beautiful, offline-accessible and shareable **single-file HTML web article**. Based on the reacticle component protocol: instead of writing raw HTML/CSS manually, use semantic components + theme-constrained Raw free layers; follow the small harness workflow of source → planning → double confirmation → generation → final review → repair, and produce long articles with 100% information retention by default. Trigger scenarios: convert URLs/PDFs/DOCX files/articles into web articles / long-form articles / briefings / explanatory articles / visual articles / tutorials / review and retrospectives / program analyses, with triggers like 'render this as a beautiful web article / turn this into a web article / generate a shareable HTML long-form article / reacticle article'. Only generate articles, not backends, forms, dashboards, product prototypes or general web apps.
Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli. Automate web interactions, take screenshots, inspect accessibility trees, debug & profile web applications. Run `playwriter skill` command to read the complete up to date skill
Web scraping skill using Firecrawl API for deep content extraction, format conversion, and page interaction. Use when you need to scrape web pages, extract structured data, take screenshots, parse PDFs, or crawl entire websites. Triggers: firecrawl, scrape, extract content, screenshot, parse pdf, crawl website, 抓取网页, 提取内容, 网页截图
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".