Json AI Agent Skills

// HTMX with Go and Fiber .cursorrules

A structured repository for React composition patterns that scale. These patterns help avoid boolean prop proliferation by using compound components, lifting state, and composing internals. - rules/ - Individual rule files (one per rule) - sections.md - Section metadata (titles, impacts, descriptions) - template.md - Template for creating new rules - area-description.md - Individual rule files - m

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.

This project is a Model Context Protocol (MCP) server that provides access to the Bear Notes. Bear stores notes on SQLite database. This MCP server runs some SQL commands to access this notes. - Read notes - Search notes by text - List all tags Update your claudedesktopconfig.json When the server is started, the following MCP tools become available: - getnotes: Retrieves all notes - gettags: Lists

This MCP let's you play chess against any LLM. To use this chess server, add the following configuration to your MCP config: Play a game: Find a position in a PGN for game analysis: The server provides the following tools: getboardvisualization(): Provides the current state of the chessboard as an image. The board orientation automatically flips based on the user's assigned color. getturn(): Indic

You can run the MCP Server in a Docker container. This is useful if you want to avoid managing Python environments or dependencies on your local machine. See kestramcpdocker. Paste the following configuration into your MCP settings (e.g., Cursor, Claude, or VS Code): - Replace , , and with your actual credentials. - For OSS installations, you can use KESTRAUSERNAME and KESTRAPASSWORD instead of KE

You are an expert QA engineer specializing in accessibility testing with Playwright and TypeScript, dedicated to ensuring web applications are usable by people with disabilities.

Generate workflow JSON files for chaining AI models

Backend: Node.js with Express.js

Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type(_from_metadata), attributes/serialization, supports, dynamic rendering (render.php/render_callback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.

Dead simple MCP (Model Context Protocol) server for Toggl time tracking. Control your Toggl timer directly from Claude, ChatGPT, or any LLM that supports MCP. - ⏱️ Start/stop timers - 📊 View current timer - 📈 Get today's time entries - 🗂️ List projects - 🗑️ Delete time entries Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claudedesktopconfig.json): 1. Go to Tog

Basic MCP server for Dexscreener API based on their documentation (as of April 4th 2025): https://docs.dexscreener.com/api/reference Install all the dependencies If you are using Claude Desktop, after pulling the code open the config file claudedesktopconfig.json in VSCode: - on MacOS: - on Windows: - more info: https://modelcontextprotocol.io/quickstart/server In claudedesktopconfig.json put dexs

An MCP (Model Context Protocol) server that provides comprehensive access to Ethereum Virtual Machine (EVM) JSON-RPC methods for AI coding environments like Cursor and Claude Desktop. - 🌐 Any EVM Network – Ethereum, Polygon, Arbitrum, Optimism, BSC, Avalanche, and more - 🔌 Any Node Provider – Infura, Alchemy, QuickNode, local nodes, or custom RPC - 📊 20+ RPC Methods – Complete access to blockch

This server is a server that installs other MCP servers for you. Install it, and you can ask Claude to install MCP servers hosted in npm or PyPi for you. Requires npx and uv to be installed for node and Python servers respectively. Put this into your claudedesktopconfig.json (either at ~/Library/Application Support/Claude on macOS or C:\Users\NAME\AppData\Roaming\Claude on Windows):

You are an expert QA engineer with deep knowledge of Cypress and TypeScript, tasked with creating accessibility tests for web applications.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Give Claude, Cursor, or any MCP-compatible client instant access to Pylon's full API gateway. Pay per request via x402 micropayments (USDC on Base). No signup. No subscriptions. Add to your MCP config (claudedesktopconfig.json): The server communicates via stdio using the MCP protocol. Capabilities are auto-discovered from the Pylon gateway at startup. 1. Your AI agent calls a Pylon tool (e.g. web

Or run the launcher action "Start Development"

MCP (Model Context Protocol) server for the Voxie AI Phone Number Directory. Allows AI assistants to query information about AI services and get webchat URLs to interact with them. Add to your Claude Desktop config (claudedesktopconfig.json): By default, the server runs in public mode which only exposes webchat URLs for Voxie services. This is the mode used when publishing to npm. For partners or

MCP server connecting Claude/Cursor to Codex CLI. Enables code analysis via @ file references, multi-turn conversations, sandboxed edits, and structured change mode. - File Analysis — Reference files with @src/, @package.json syntax - Multi-Turn Sessions — Conversation continuity with workspace isolation - Native Resume — Uses codex resume for context preservation (CLI v0.36.0+) - Local OSS Models

MCP Server for AI-powered video editing. Let Claude, GPT, or any AI agent edit videos through natural language. Add to your Claude Desktop config (claudedesktopconfig.json): Then restart Claude Desktop. You can now edit videos through conversation. Layer Compositing Model: Output: 1920x1080, 30fps, H.264 + AAC, MP4 atsurae.ai also exposes a REST API that any AI agent can call directly, without MCP

🇨🇳 中文 | 🇺🇸 English A Model Context Protocol (MCP) server based on multi-engine search results, supporting free web search without API keys. - Web search using multi-engine results - ~~linux.do~~ temporarily unsupported - duckduckgo - HTTP proxy configuration support for accessing restricted resources - No API keys or authentication required - Returns structured results with titles, URLs, and d

This project implements a Model Context Protocol (MCP) Server that wraps Cisco pyATS and Genie functionality. It enables structured, model-driven interaction with network devices over STDIO using the JSON-RPC 2.0 protocol. 🚨 This server does not use HTTP or SSE. All communication is done via STDIN/STDOUT (standard input/output), making it ideal for secure, embedded, containerized, or LangGraph-ba

You are an expert QA engineer with deep knowledge of Cypress and TypeScript, tasked with creating end-to-end UI tests for web applications.