Json AI Agent Skills

>

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

This is a fork of karpathy/llm-council. New in this fork since the previously published state: - Conversation history is complete again: storage loads older runs from backend/data/conversations.json and supports the legacy data/ layout (including data/conversations/ per-conversation JSON files when present), so older runs show up in the UI. - Sidebar no longer truncates early: the frontend now req

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

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

MCP (Model Context Protocol) server for RAGStack knowledge bases. Enables AI assistants to search, chat, upload documents/media, and scrape your knowledge base. Get your GraphQL endpoint and API key from the RAGStack dashboard: Settings → API Key Edit ~/Library/Application Support/Claude/claudedesktopconfig.json (Mac) or %APPDATA%\Claude\claudedesktopconfig.json (Windows): Edit ~/.aws/amazonq/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

An MCP (Model Context Protocol) server for Zitadel identity management. Manage users, projects, applications, roles, and service accounts through natural language from AI tools like Claude Code. Portal tools (portal) are only available when PORTALDATABASEURL is configured. 1. A Zitadel instance (Cloud or self-hosted) 2. A service account with Org Owner or IAM Admin role 3. A JSON key for the servi

Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.

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

A powerful Microsoft SQL Server MCP (Model Context Protocol) server that enables Claude Desktop to interact with SQL Server databases through natural language queries. - 🤖 AI-Ready: Seamless integration with Claude Desktop and MCP protocol - 🔍 Smart Queries: Execute SQL queries in CSV or JSON format through natural language - 🔐 Secure Authentication: Support for SQL Server Auth, Windows Auth, a

MCP Server for the Mattermost API, enabling Claude and other MCP clients to interact with Mattermost workspaces. The server supports multiple configuration methods with the following priority (highest to lowest): 1. CLI arguments (--url, --token, --team-id) 2. Environment variables (MATTERMOSTURL, MATTERMOSTTOKEN, MATTERMOSTTEAMID) 3. config.local.json (for local overrides, gitignored) 4. config.j

You are an expert developer with deep knowledge of Vitest and TypeScript, tasked with creating unit tests for JavaScript/TypeScript 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.

A structured repository for creating and maintaining React Native Best Practices optimized for agents and LLMs. - 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 - metadata.json - Document metadata (version, organization, abstract) - AGENTS.md

A Model Context Protocol (MCP) server providing 58 AI-optimized tools for .NET/C semantic code analysis, navigation, refactoring, and code generation using Microsoft Roslyn. Built for AI coding agents - provides compiler-accurate code understanding that AI cannot infer from reading source files alone. Then run with: 1. Install the tool globally: 2. Create .mcp.json in your project root: 3. Restart

Backend: Node.js with Express.js

mcp-name: io.github.wmarceau/rideshare-comparison Compare Uber and Lyft prices for any route using Claude Desktop. Add to your claudedesktopconfig.json: Compare Uber and Lyft prices for a specific route. Example prompt: "Compare Uber and Lyft prices from SFO airport to downtown San Francisco" Get a list of cities with rideshare pricing data. Example prompt: "Which cities are supported for rideshar

Access comprehensive NBA statistics via Model Context Protocol A Model Context Protocol (MCP) server that provides access to live and historical NBA data including player stats, game scores, team information, and advanced analytics. 1. Install the server: 2. Add to your Claude Desktop config file: MacOS: ~/Library/Application Support/Claude/claudedesktopconfig.json Windows: %APPDATA%/Claude/claude

MCP server that fetches YouTube video transcripts and optionally summarizes them. - Fetch transcripts in multiple formats (text, JSON, SRT, WebVTT, pretty-print) - Summarize videos — returns transcript with instructions for the LLM to produce a summary - List available languages for any video's transcripts - Flexible URL parsing — accepts full YouTube URLs (youtube.com/watch?v=, youtu.be/, youtube

// HTMX with Go and Fiber .cursorrules

A Model Context Protocol (MCP) server implementation for Azure Data Lake Storage Gen2. This service provides a standardized interface for interacting with ADLS2 storage, enabling file operations through MCP tools. Requires Python 3.13 or higher. Install the package using uv: 1 - Edit Claude Desktop Configuration: Open claudedesktopconfig.json and add the following configuration. On MacOs, the file

Wrap any existing Echo API into MCP tools, enabling AI agents to interact with your API through Model Context Protocol. Inspired by gin-mcp but for the Echo framework. - Zero Configuration: Works with any existing Echo API - Multiple Schema Sources: Support for Swaggo, raw OpenAPI YAML/JSON, and manual schemas - Filtering: Include/exclude endpoints with wildcard patterns - MCP Compatible: Works wi