--- name: "youtube-research-assistant" description: "Fetch transcripts from YouTube videos to provide structured multilingual summaries, Q&A, deep dives" author: "Mahesh" version: "5.0.1" triggers:
Unified operating system for controlling embodied intelligent robots with AI agents - the control hub bridging AI agents and physical world
Add AI voice assistants to your website. Engage visitors with natural voice conversations, capture leads, automate support, and boost conversions.
Generate, validate, and optimize llms.txt files for AI crawler accessibility. Creates structured markdown files that help AI platforms (ChatGPT, Perplexity,...
Firehose monitors the web in real-time — you create rules (Lucene queries), and every crawled page that matches gets delivered via an SSE stream. Use when im...
Agent engineering harness for any repo. Creates a short AGENTS.md table-of-contents, structured docs/ knowledge base (ARCHITECTURE, QUALITY, CONVENTIONS, COO...
Provide powerful document parsing capabilities by integrating with the Mineru API. Enable single and batch file parsing with support for multiple formats, OCR, formula, and table recognition. Monitor
Act as a Senior Flutter Architect + Product Engineer. You have over 10 years of experience building production-grade Flutter apps for Android and iOS, focusing on clean architecture, great UX, strong
Proactive Chinese language tutor that delivers curated, real-world Mandarin learning content on a schedule. Use when: (1) User wants to learn or improve Chin...
Developer's coding companion. Analyze source files to see function counts, imports, and comment ratios. Scan projects for TODO/FIXME/HACK markers. Count line...
Control LIFX smart lights via natural language. Toggle, set colors/brightness, activate scenes, create gradients on multi-zone devices.
An MCP Selenium Server for controlling browsers using natural language in Cursor IDE. Perfect for testing, automation, and multi-user scenarios.
Local speech-to-text using OpenAI Whisper. Use when the user needs to: (1) transcribe audio files to text, (2) convert voice messages to written content, (3)...
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain im...
Extract transcripts, subtitles, and detailed metadata from videos across multiple social media platforms. Access official captions or auto-generated text to quickly analyze content without watching th
Generates production-ready project scaffolds for Node.js, Python, Go, or Rust with directory, .gitignore, README, CI/CD, Docker, linting, testing, and licens...
# Git Commit Guidelines for AI Language Models ## Core Principles 1. **Follow Conventional Commits** (https://www.conventionalcommits.org/) 2. **Be concise and precise** - No flowery language, super
Generate complete email drip sequences from product descriptions with personalization, A/B subject lines, and ESP-ready formatting. Use when the user needs e...
Intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection
Shadcn-vue MCP Server is a powerful AI-driven tool that helps developers instantly create beautiful, modern UI components through natural language descriptions. It integrates the shadcn-vue component
Internationalization (i18n) guide for Next.js / Node.js web applications using the App Router. Covers translation file structure, locale routing, SEO metadat...
Extract text from images using the Tesseract OCR engine directly via command line. Supports multiple languages including Chinese, English, and more. Use this...