Anthropic API Agent Skills

|

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.

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.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

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.

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.

Persistent memory compression system built for Claude Code. Gives your AI agent long-term memory across sessions with automatic context compression and retrieval.

Compress images for web/SEO performance using cwebp. Use when optimizing images for faster page loads, reducing file sizes, or converting JPG/PNG to WebP format.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

AgentSys A modular runtime and orchestration system for AI agents.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Version: v0.2.0 An MCP server that provides access to the Postman API. Functionality is based on the official OpenAPI specification. For more information, see the Postman API documentation. This project is part of the Model Context Protocol (MCP) initiative from Anthropic. For more information, visit the MCP GitHub repository and the announcement on the Anthropic blog. Skip ahead to install instru

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

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

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.

Claude Code forgets everything between sessions. Built-in auto-memory exists but: - It's opaque (Claude decides what's "meaningful") - Limited to 200 lines loaded at startup - Not tightly integrated into the agentic loop - No hierarchical organization (scales poorly) A skill-based memory protocol with: - Hierarchical storage: core.md summaries → topics/ .md details - Background agents: Memory ops

- ✅ Claude Code Integration - Optimized for use with Anthropic's Claude Code CLI - ✅ SSH Tunnel Support - Built-in support for SSH tunnels to remote databases - ✅ Auto-start/stop Hooks - Automatic tunnel management with Claude start/stop - ✅ DDL Operations - Added MYSQLDISABLEREADONLYTRANSACTIONS for CREATE TABLE support - ✅ Multi-Project Setup - Easy configuration for multiple projects with diffe

Plugins for Claude Code. Your world at a glance, without leaving the terminal. Track PRs, calendar, Slack, stocks, music—all in your statusline. The flow: /hub-setup → add monitors → alerts appear → /hub-ack for smart actions (merge PR, join meeting, reply to Slack). → Full documentation — workflow examples, all services, commands AI-powered market screening, without leaving the terminal. Screen s

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

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.

Transform how you access and interact with your team's knowledge by connecting Claude, Cursor AI, and other AI assistants directly to your Confluence spaces, pages, and documentation. Get instant answers from your knowledge base, search across all your spaces, and streamline your documentation workflow. - Ask AI about your documentation: "What's our API authentication process?" - Search across all

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

Educational MCP server with 17 tools, persistent workspace, and cloud hosting. Built with FastMCP and the official Model Context Protocol Python SDK. Available on: - Official MCP Registry - io.github.clouatre-labs/math-mcp-learning-server - PyPI - math-mcp-learning-server Requires an MCP client: - Claude Desktop - Anthropic's desktop app - Claude Code - Command-line MCP client - Goose - Open-sourc

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