Gemini AI Agent Skills

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence.

A Model Control Protocol (MCP) server for managing and serving dynamic prompt templates using elegant and powerful text template engine. Create reusable, logic-driven prompts with variables, partials, and conditionals that can be served to any compatible MCP client like Claude Code, Claude Desktop, Gemini CLI, VSCode with Copilot, etc. - MCP Compatible: Works out-of-the-box with any MCP client tha

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

Give any AI the ability to build, validate, and deploy production multi-agent systems. This is an MCP server that connects AI assistants — ChatGPT, Claude, Gemini, Copilot, Cursor, Windsurf, and any MCP-compatible environment — directly to the ADAS platform. An AI developer says "Build me a customer support system with order tracking and escalation" — and their AI assistant handles the entire life

A modern, cross-platform Model Context Protocol (MCP) server that enables AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently. The Gopher & Gemini MCP Server bridges vintage and modern alternative internet protocols with AI assistants, allowing LLMs like Claude to explore the unique content and communities that thrive on both Gophersp

Finally, MCP servers & commands that just work on Windows. Every MCP server README assumes macOS or Linux. You copy the config, paste it in, and nothing happens — because npx, uvx, and friends are .cmd batch shims on Windows, not real executables. mcp2win fixes this by wrapping commands with cmd.exe /c so your MCP servers actually start. Works with Claude Code/Desktop, VS Code, Cursor, Zed, Amazon

Your AI keeps breaking things you told it not to touch. SpecLock makes it stop. Website · npm · Smithery · GitHub Developed by Sandeep Roy · Free & Open Source (MIT License) 100/100 on Claude's independent test suite. 929 tests across 18 suites. 0 false positives. 15.7ms per check. Gemini Flash hybrid, Spec Compiler, Code Graph, Typed Constraints, Python SDK, ROS2 integration. That's it. One c

Want to use GPT-5, Gemini, or DeepSeek in Claude Code? Today you need to: 1. Create accounts with 5+ AI providers 2. Manage 5+ API keys and billing systems 3. Pay $20-100/month minimums per provider 4. Configure each provider separately That's too much friction. BlockRun MCP gives you access to 30+ AI models with: - Zero API keys - No accounts needed with OpenAI, Google, etc. - One wallet - Single

A Model Context Protocol (MCP) server that allows interacting with the CipherTrust RestFul Data Protection (CRDP) service. This MCP server enables AI applications and LLMs to securely protect and reveal sensitive data through the CipherTrust CRDP service. It supports both individual and bulk protect and reveal operations with versioning support. - Video 1: [https://youtu.be/O2pQRoykaaU] - Deployme

A local Model Context Protocol (MCP) server that provides structured, high-signal insight into a Git repository, enabling AI coding agents to understand project state, structure, activity, and risk — without uploading or modifying the codebase. AI coding agents (Claude Code, Cursor, Codex, Gemini, etc.) are powerful, but they lack situational awareness when working with non-trivial codebases. They

mcp-trinv-server (ou MCPTRINV) est un serveur de type MCP (Model Context Protocol) qui est utilisé pour augmenter les ressources d'assistant d'Intelligence Artificielle comme Claude ou Gemini. MCPTRINV permet de rechercher des communes à partir d'un fragment de leur nom puis de rechercher des parcelles cadastrales dans une commune ayant une surface donnée. Il s'appuie sur le site TRINV. - trinv-ch

+W is a universal "save for later" action for commerce. This MCP server lets AI assistants save any product URL to a user's Wishfinity wishlist with one click. Works with Claude, ChatGPT, Gemini, LangChain, OpenAI Agents SDK, and any MCP-compatible client. When an AI recommends a product, it can offer +W Add to Wishlist. The user clicks the link, and the product is saved to their Wishfinity accoun

English | 日本語 mcp-alphabanana is a Model Context Protocol (MCP) server for generating image assets with Google Gemini. It is built for MCP-compatible clients and agent workflows that need fast image generation, transparent outputs, reference-image guidance, and flexible delivery formats. Keywords: MCP server, Model Context Protocol, Gemini AI, image generation, FastMCP Key capabilities: - Ultra-fa

A Model Context Protocol (MCP) server for GitLab and Jira integration. This server allows AI agents like gemini-cli to interact with your GitLab and Jira instances. - Projects: List all accessible projects or filter them by name. - Merge Requests: List merge requests for a project, get detailed information (including diffs), add comments, and assign reviewers. - Pipeline/CI/CD: Get pipeline status

Drive four external coding CLIs — Google's Antigravity (Gemini 3.6 Flash), OpenAI Codex, the GitHub Copilot CLI, and Cursor — as sub-agents inside Claude Code. Text answers, image generation, real repo work, and parallel swarms, on quota you already pay for. One MCP server, four backends. It exposes Google Antigravity, OpenAI Codex, the GitHub Copilot CLI, and Cursor to Claude Code as clean MCP to

Multi-agent orchestration platform for enterprise AI development. Run 12+ AI agents concurrently with full governance, Gemini-powered code review, and enforced quality gates. Solves coordination, verification, and metrics challenges that stall enterprise AI adoption.

A multi-model AI orchestration MCP server for automated code review and LLM-powered analysis. Multi-MCP integrates with Claude Code CLI to orchestrate multiple AI models (OpenAI GPT, Anthropic Claude, Google Gemini) for code quality checks, security analysis (OWASP Top 10), and multi-agent consensus. Built on the Model Context Protocol (MCP), this tool enables Python developers and DevOps teams to

Built by Matious — We build custom AI tools and MCP servers for businesses. Managing Google Ad Manager is tedious. Creating campaigns, uploading creatives, and configuring line items involves countless clicks through a complex UI. This MCP server changes that. Connect it to Claude and manage your entire ad operations through conversation: - "Create a new campaign for Nike ending December 31st" - "

A professional Model Context Protocol (MCP) server that provides a comprehensive toolkit for interacting with Instagram. This server enables LLMs (like Claude or Gemini) to manage accounts, analyze social graphs, discover content, and engage with the Instagram community directly from their interface. - Full Account Control: Edit profile, manage privacy, and track activity. - Advanced Messaging: Re

Seamlessly integrate Wolfram Alpha into your chat applications. This project implements an MCP (Model Context Protocol) server designed to interface with the Wolfram Alpha API. It enables chat-based applications to perform computational queries and retrieve structured knowledge, facilitating advanced conversational capabilities. Included is an MCP-Client example utilizing Gemini via LangChain, dem

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

Build and publish websites through AI conversation. Create pages, upload assets, manage data, and deploy to custom domains — all from your favorite AI assistant. Just connect and start talking. 1. Open Le Chat → Intelligence → Connectors → + Add Connector 2. Choose Custom MCP Connector 3. Enter URL: https://mcp.websitepublisher.ai/ 4. Click Connect → Login → Done ✅ Add to your claudedesktopconfig.

Write less code and say less about it. Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness. It works with Claude (claude.ai and the API), Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline, OpenClaw, Kiro, and Kilo Code. Three independent

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.