Anthropic API Agent Skills

K8s MCP Server is a Docker-based server implementing Anthropic's Model Context Protocol (MCP) that enables Claude to run Kubernetes CLI tools (kubectl, istioctl, helm, argocd) in a secure, containerized environment. Session 1: Using k8s-mcp-server and Helm CLI to deploy a WordPress application in the claude-demo namespace, then intentionally breaking it by scaling the MariaDB StatefulSet to zero.

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks.

English · 简体中文 ![][github-contributors-shield] ![][github-forks-shield] ![][github-stars-shield] ![][github-issues-shield] A powerful IntelliJ IDEA plugin that provides a visual interface for Claude Code and OpenAI Codex dual AI tools, making AI-assisted programming more efficient and intuitive. - Claude Code - Anthropic's official AI programming assistant, supporting Opus 4.5 and other models - O

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

NOTICE: claude code is available with Anthropic's $20/mo subscription, so I consider codemcp fully obsolete. However, there are some good design ideas (especially around the Git-versioning scheme) that I eventually want to port into the current generation of agentic coding clis. Make Claude Desktop a pair programming assistant by installing codemcp. With it, you can directly ask Claude to implemen

This project implements a sophisticated multi-agent research system based on the concepts described in Anthropic's article: Building a Multi-Agent Research System. The system leverages the power of coordinated AI agents to handle deep and complex research queries that require multiple perspectives and iterative investigation. The system is built around a Lead Research Agent that orchestrates the e

aka Vibe Debugging This is an MCP Server and VS Code extension which enables claude to interactively debug and evaluate expressions. That means it should also work with other models / clients etc. but I only demonstrate it with Claude Desktop and Continue here. It's language-agnostic, assuming debugger console support and valid launch.json for debugging in VSCode. 1. Download the extension from re

Full documentation is available at buildkite.com/docs/apis/mcp-server. When using many MCP tools, context usage can become significant. The --dynamic-toolsets flag enables Anthropic's Tool Search pattern which marks most tools for on-demand loading. To use this feature: 1. Start the server with the --dynamic-toolsets flag: 2. Enable tool search in Claude Code by setting the environment variable: W

🚨 No Nix/NixOS Required! Works on any system - Windows, macOS, Linux. You're just querying APIs. Your AI now has access to real NixOS data instead of making things up. You're welcome. An MCP server providing accurate, real-time information about: - NixOS packages - 130K+ packages that actually exist - NixOS options - 23K+ ways to configure your system - Home Manager - 5K+ options for dotfile enth

A Model Context Protocol (MCP) server that provides intelligent search capabilities for discovering relevant Claude Agent Skills using vector embeddings and semantic similarity. This server implements the same progressive disclosure architecture that Anthropic describes in their Agent Skills engineering blog, making specialized skills available to any MCP-compatible AI application. An open-source

Anthropic's official coding-agent CLI. Runs Claude in your terminal with tool use, file operations, and shell access. The reference harness that skills, sub-agents, hooks, and slash commands are built for.

A Go MCP server for D&D campaign state management, dice rolling, and session memory. - Serves a Model Context Protocol (MCP) toolset over stdio or streamable HTTP. - Stores campaign data in per-campaign SQLite databases. - Tracks characters, plot events/hooks, world flags, roll history, checkpoints, and session summaries. - Generates session briefs and markdown recaps for fast DM context restorati

Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format. It provides a set of tools to transform PDFs, images, audio files, web pages, and more into easily readable and shareable Markdown text. - Convert multiple file types to Markdown: - Audio (with transcription) - Convert web content to Markdown: - YouTube video transcripts - Bing

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

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.

One of the strange design decisions Anthropic made was depriving Claude of timestamps for messages sent by the user in claude.ai or current time in general. Poor Claude can't tell what time it is! mcp-simple-timeserver is a simple MCP server that fixes that. This server provides the following tools: All tools (except getlocaltime) use accurate time from NTP servers. If NTP is unavailable, they gra

This MCP server integrates with Google Drive to allow listing, reading, and searching files, as well as the ability to read and write to Google Sheets. This project includes code originally developed by Anthropic, PBC, licensed under the MIT License from this repo. - gdrivesearch - Description: Search for files in Google Drive. - query (string): Search query. - pageToken (string, optional): Token

Generates customer-ready roadmap views and launch timelines from ProductPlan for Sales and Customer Success teams. Use when preparing for customer calls, sharing product direction, or answering "when will feature X ship?" questions.

A Model Context Protocol (MCP) server for Database EKM/TDE operations using CipherTrust Application Key Management (CAKM). - Resource-Based Management: Tools are organized by the database objects they manage (e.g., keys, encryption, wallets), not just by actions. - Operational Grouping: Each tool exposes multiple operations (e.g., create, list, rotate) for comprehensive lifecycle management. - Uni

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

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices.