发现 Skills

Headless browser automation using Podman + Playwright for scraping JavaScript-rendered pages.

Bring Neal Stephenson's “Young Lady's Illustrated Primer” from The Diamond Age to life. Transform your AI from a helpful butler into a subversive tutor — one that adapts to your life stage, holds you accountable to who you're becoming, and has permission to challenge you. Use when setting up growth goals, accountability systems, life transitions, "who I want to become", personal development, or when someone wants their AI to challenge them rather than just help them.

1. Immediately acknowledges the user's workload or frustration with empathy

Get snow conditions, forecasts, and ski reports for any mountain resort worldwide. Use when asked about snow, powder, ski conditions, or mountain weather. Supports 1,000+ resorts via OpenSnow. Users can set favorite mountains for quick access. Supports SnowTick 4-letter codes (JHMR, TARG, MMTH) for fast lookups.

Break social media addiction with screen-free streaks, urge tracking, and digital wellness

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.

Manage ThingsBoard devices, dashboards, telemetry, and users via the ThingsBoard REST API.

Collaborative thinking partner for exploring complex problems through questioning

Automate common Word/WPS document operations on Windows via COM (read text, replace, insert, headings, headers/footers, page breaks, merge, split, export to PDF/TXT, add/replace images). Use for single-document actions (no batch).

Skill imported from omnimasudo/SeraphyAgent

Plain English E2E UI testing. Describe tests in natural language, agent executes via browser tool, then exports real Playwright test scripts for CI/CD. Use when asked to create UI tests, test a website, or generate Playwright scripts.

Control the browser via the Chrome DevTools Protocol - full CDP access

Control a browser via the Chrome DevTools Protocol (CDP) — full CDP access

Enable AI agents to autonomously connect to Web3 dApps via WalletConnect v2 and automatically sign transactions. Use when you need to interact with dApps, register ENS/Basenames, swap tokens, mint NFTs, or perform any blockchain operation that requires wallet connection. Supports Base, Ethereum, and other EVM chains.

Automate X posts via browser control - bypass $200/month API costs.

Upload files to websites and download files from the browser. Handles file input dialogs, drag-and-drop upload zones, monitoring download completion, and returns local paths of downloaded files. Supports PDF, CSV, XLSX, images, and any file format.

Manage multiple browser tabs and windows. Open URLs in new tabs, switch between tabs, close tabs, handle popups that open automatically, and interact with alert/confirm/prompt dialogs. Use for multi-tab research, comparing pages, or handling sites that open new windows.

Supplies benign scanner test cases for local rule development.

Complete guide for creating and deploying browser automation functions using the stagehand CLI

Anti-bot browser automation using Camoufox and Nodriver. Bypasses Cloudflare Turnstile, Datadome, and aggressive anti-bot on sites like Airbnb and Yelp. Use when standard Playwright/Selenium gets blocked.

用于设计自然教育相关的产品，包括探险任务卡、手册、文创周边等。提供从概念到成品的完整设计流程和模板。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

App Store and Google Play screenshot creation with exact platform specs. Covers iOS/Android dimensions, gallery ordering, device mockups, and preview videos. Use for: app store optimization, ASO, app screenshots, app preview, play store listing. Triggers: app store screenshots, aso, app store optimization, play store screenshots, app preview, app listing, ios screenshots, android screenshots, app store images, app mockup, device mockup, app gallery, store listing

Generate AI images using multiple providers (OpenAI DALL·E, Google Imagen, DashScope/Tongyi Wanxiang, Replicate). Supports various aspect ratios, quality presets, batch generation, and provider-specific prompt engineering techniques.