productivity▌

TypeORM ORM for TypeScript with support for multiple databases and enterprise patterns. \n \n Supports Active Record and Data Mapper patterns with TypeScript decorators for entity and column definitions \n Works across Node.js, browsers, mobile platforms (React Native, Ionic, Cordova), and desktop environments (Electron) \n Includes Query Builder for complex queries, custom repositories, transactions, and first-class migration support \n Integrates seamlessly with NestJS via TypeOrmModule and pr

路由规则：

Clone any website with pixel-perfect fidelity using an orchestrated multi-agent workflow.

Search WeChat public account articles by keyword with title, summary, publish time, and source information. \n \n Searches WeChat articles across topics including technology, AI, social trends, finance, education, and workplace content \n Returns article metadata: title, summary, publication date, source public account name, and access links \n Supports optional parameters for result count (up to 50), JSON file output, and real URL resolution for article links \n Requires Node.js with the cheeri

Search DuckDuckGo from the terminal using ddgr.

Trigger this skill when the user wants:

Extract clean markdown from web pages, removing clutter and navigation to minimize token usage. \n \n Converts web page content to readable markdown using the --md flag, stripping ads, navigation, and boilerplate \n Supports output to file with -o flag and extraction of specific metadata properties (title, description, domain) via -p \n Offers multiple output formats: markdown, JSON with both HTML and markdown versions, or raw HTML \n Preferred alternative to WebFetch for standard web pages, doc

Multilingual speech recognition with 99 languages, transcription, translation, and six model sizes from 39M to 1550M parameters. \n \n Supports transcription, translation to English, language identification, and word-level timestamps across 99 languages trained on 680,000 hours of audio \n Six model sizes (tiny through large) with configurable speed/quality tradeoffs; turbo model offers 8× speedup over large with comparable quality \n GPU acceleration delivers 10–20× faster processing; CPU trans

Meme token discovery, developer reputation checks, bundle detection, and co-investor tracking for pump.fun and similar launchpads. \n \n Scans new token launches across Solana, BSC, X Layer, and TRON with filtering by stage (NEW, MIGRATING, MIGRATED) and protocol \n Analyzes developer reputation including rug pull history, past token migrations, and holding concentration to assess creator credibility \n Detects bundler and sniper activity on specific tokens, plus identifies wallets that co-inves

Use this skill when you need to: