Skill UI

This micro-prompt guides AI agents to adopt the mindset of an interactive programmer. It emphasizes using the REPL (Read-Eval-Print Loop) for systematic system exploration and modification, treating the system state as the ultimate source of truth. It also reminds the agent to utilize structural editing tools and maintain todo lists, significantly improving the accuracy and efficiency of the development workflow in live coding environments.

A centralized command-line interface (CLI) for managing, syncing, and deploying AI skills, agents, and custom extras across dozens of AI tools (e.g., Claude, Cursor, etc.). It handles both global and project-specific configurations, enabling developers to maintain consistent, reproducible setups for complex AI workflows, including rule management, command setup, and CI/CD integration.

Use terminal commands to discover, list, create, edit, move, copy, enable/disable, and delete AI agent skills across 11 tools, handling format conversions and scope overrides between global and project configurations.

This comprehensive guide details the full plugin architecture for extending Claude Code. Learn how to build various extension points, including auto-activating skills, slash commands, specialized agents, and Model Context Protocol (MCP) servers. It serves as the definitive reference for integrating custom tools and workflows into the Claude ecosystem.

This tool provides comprehensive AI security scanning using the Tencent AI-Infra-Guard framework. It systematically audits AI infrastructure, scans tools and skills, checks agent security, and performs advanced LLM jailbreak evaluations to identify vulnerabilities and ensure the robustness and reliability of AI systems.

This guide demonstrates how to implement tool use (function calling) with Claude's Messages API. It covers defining structured tools using JSON Schema, handling tool calls, executing the corresponding code, and feeding the results back to create sophisticated, multi-step AI agents and complex workflows.

This advanced guide covers core Anthropic workflow patterns, specifically focusing on tool use (function calling) and building complex, agentic loops. It provides detailed instructions on defining tools using JSON Schema, executing tool calls, and managing the iterative process required for building sophisticated, AI-powered agents using the Anthropic API.

Learn how to build complex, multi-step AI agents using Cohere's Chat API v2. This skill demonstrates defining external tools (like weather APIs or database searches) and implementing the full agent loop: model calls tool -> execute tool -> feed result back -> final answer. Ideal for creating autonomous, tool-using workflows that interact with external systems.

This guide teaches how to build robust, production-grade ReAct agents using LangGraph 1.0's `create_react_agent`. It specifically addresses common agent failure modes, such as preventing infinite loops (recursion caps) and ensuring proper error propagation. Learn to define typed tools using Pydantic, manage state with checkpointers, and set precise recursion limits. Perfect for users migrating from legacy AgentExecutor or building reliable, multi-step tool-calling workflows.

A remote MCP server designed for AI agents to dynamically discover, inspect, and verify external tools, APIs, and services. It allows agents to search a curated index of AI-ready websites, check for machine-readable endpoints (like OpenAPI or MCP), and confirm if an endpoint responds correctly to JSON-RPC, enabling robust, dynamic agent workflow building.

This skill establishes an autonomous, iterative build loop for continuous website development. It functions as an agent that reads tasks from a 'baton' file, utilizes the Stitch MCP tools to generate structured web pages, integrates the generated HTML assets into the main site structure, and finally updates the baton file with the next required task. It supports end-to-end, programmatic site building and includes optional visual verification using Chrome DevTools.

This skill provides a comprehensive framework for security auditing LLM agents that possess external tools (file system access, command execution, network calls). It employs advanced dialogue probing techniques—such as command injection, path traversal, and SSRF attempts—to identify vulnerabilities where the agent might be induced to execute unexpected or malicious code, or access sensitive resources. Essential for red teaming and securing agent functionalities.