LLM & AI Agent Skills

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Guide for upgrading Stripe API versions and SDKs

mcp-ragchat An MCP server that adds RAG-powered AI chat to any website. One command from Claude Code. Tell Claude Code "add AI chat to mysite.com" and it will crawl your content, build a local vector store, spin up a chat server, and hand you an embed snippet. No cloud infra. No database. Just one API key. 1. Clone and build 2. Configure Claude Code (~/.claude/mcp.json) Open Claude Code and say: C

This MCP (Model Context Protocol) server provides various tools to interact with dbt. You can use this MCP server to provide AI agents with context of your project in dbt Core, dbt Fusion, and dbt Platform. Read our documentation here to learn more. This blog post provides more details for what is possible with the dbt MCP server. We publish an experimental Model Context Protocol Bundle (dbt-mcp.m

Zero-hallucination answers • Gemini Deep Research • 14 Security Layers • Enterprise Compliance What's New 2026 • Deep Research • Document API • Create Notebooks • Security • Install - 🔍 Query your NotebookLM notebooks — source-grounded, zero-hallucination answers - 📚 Create & manage notebooks programmatically — no manual clicking - 🎙️ Generate audio overviews — podcast-style summaries of your d

Overview • Quick Start • Supported Data Providers • FinData is an open-source Model Context Protocol(MCP) Server that provides professional financial data access capabilities for LLM. It supports various data providers such as Tushare, Wind, DataYes, etc. This enables AI applications to quickly retrieve financial data. Fully supports both Stdio and SSE transports, offering flexibility for differen

Transcribe MCP Automate your transcriptions with AI. Transcribe MCP instantly connects your account to assistants like Claude, Windsurf, Cursor, and more so they can automate tasks on your behalf. The Local Server can add local files for transcription and return result to your Assistant in seconds. - ⚡ Fast, lightweight and LLM-friendly. No special ASR models needed, no setup and fighting python p

The Mermaid MCP Server enables AI assistants like GitHub Copilot, Claude, and custom LLM applications to generate professional architecture diagrams, flowcharts, sequence diagrams, and more using natural language. It provides a Model Context Protocol interface for seamless integration with AI coding assistants. - 🤖 AI-Powered Generation: Create diagrams using natural language with GitHub Copilot

A Model Context Protocol (MCP) server that loads and serves multiple OpenAPI specifications to enable LLM-powered IDE integrations. This server acts as a bridge between your OpenAPI specifications and LLM-powered development tools like Cursor and other code editors. - Loads multiple OpenAPI specifications from a directory - Exposes API operations and schemas through MCP protocol - Enables LLMs to

An MCP server that provides safe access to your iMessage database through Model Context Protocol (MCP). This server is built with the FastMCP framework and the imessagedb library, enabling LLMs to query and analyze iMessage conversations with proper phone number validation and attachment handling. - macOS (required for iMessage database access) - Python 3.6+ Install all required dependencies: - fa

An MCP (Model Context Protocol) server that provides token-efficient access to OpenAPI (v3.0) and Swagger (v2.0) specifications via MCP Resource Templates. The primary goal of this project is to allow MCP clients (like Cline or Claude Desktop) to explore the structure and details of large OpenAPI specifications without needing to load the entire file into an LLM's context window. It achieves this

A Model Context Protocol (MCP) server that interfaces with the AniList API, allowing LLM clients to access and interact with anime, manga, character, staff, and user data from AniList. - Search for anime, manga, characters, staff, and studios - Get detailed information about specific anime, manga, characters, and staff members - Access user profiles and lists - Support for advanced filtering optio

This project provides Model Context Protocol (MCP) for the Mifos X Ecosystem, enabling AI agents to access financial data and operations. Implementations is available in Java (Quarkus). Use the MCP Inspector to test and debug your server: This starts a local web UI to connect to your MCP server via STDIO or SSE. Prerequisites: JDK 21+, Maven 1. Configure environment variables in your shell or IDE:

🚀 1:1 Optimized Rust Implementation of WCGW (What Could Go Wrong) 🚀 Winx is a specialized Model Context Protocol (MCP) server that provides high-performance tools for LLM code agents. It implements the core functionality of WCGW in pure Rust for maximum efficiency and stability. Benchmarks on i9-13900K + RTX 4090 (WSL2) - Rust 1.75+ - Linux / macOS / WSL2 Add to ~/.config/Claude/claudedesktopcon

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

Smart context management for LLM development workflows. Share relevant project files instantly through intelligent selection and rule-based filtering. Getting the right context into LLM conversations is friction-heavy: - Manually finding and copying relevant files wastes time - Too much context hits token limits, too little misses important details - AI requests for additional files require manual

A Model Context Protocol (MCP) server for accessing the Climatiq API to calculate carbon emissions. This allows AI assistants to perform real-time carbon calculations and provide climate impact insights. This MCP server integrates with the Climatiq API to provide carbon emission calculations for AI assistants: - set-api-key: Configure the Climatiq API key used for authentication - electricity-emis

Piston MCP Server piston-mcp is an MCP server that allows LLMs to connect to and execute code using Piston . You can try out piston-mcp locally without cloning it. To try out piston-mcp you'll need to install uv: You will also need to download an MCP client to connect to piston-mcp, such as Claude Desktop. Update the MCP client's configuration with the following configuration to connect to piston-

An MCP server for Timeplus. generatesql to give LLM more knowledge about how to query Timeplus via SQL - Execute SQL queries on your Timeplus cluster. - Input: sql (string): The SQL query to execute. - By default, all Timeplus queries are run with readonly = 1 to ensure they are safe. If you want to run DDL or DML queries, you can set the environment variable TIMEPLUSREADONLY to false. listdatabas

Recursive Decomposition Skill Handle long-context tasks with Claude Code through recursive decomposition What It Does • Installation • How It Works • Benchmarks • Acknowledgments When analyzing large codebases, processing many documents, or aggregating information across dozens of files, Claude's context window becomes a bottleneck. As context grows, "context rot" degrades performance: - Missed de

Transform how you work with Bitbucket by connecting Claude, Cursor AI, and other AI assistants directly to your repositories, pull requests, and code. Get instant insights, automate code reviews, and streamline your development workflow. - Ask AI about your code: "What's the latest commit in my main repository?" - Get PR insights: "Show me all open pull requests that need review" - Search your cod