Skill UI

Provides best practices for configuring Large Language Model (LLM) access, specifically for Anthropic Claude, across development, staging, and production environments. This guide details setting up separate API keys, selecting appropriate models (e.g., Haiku, Sonnet, Opus), and managing unique rate limits for robust, scalable, and secure LLM integration in enterprise systems.

A comprehensive checklist designed to ensure Claude-powered applications are robust, secure, and production-ready before going live. It guides developers through critical areas, including robust error handling, API security best practices, cost control mechanisms, real-time monitoring setup, and performance optimization, ensuring a stable user experience.

A comprehensive guide to production-ready patterns for integrating with Anthropic's Claude API using both TypeScript and Python SDKs. Covers robust client setup (retries, timeouts), advanced error handling, streaming implementations, prompt caching, and batch processing to ensure high performance and cost efficiency in real-world AI applications.

This guide details essential best practices for securing applications integrated with Anthropic's Claude API. It covers critical security measures including secure API key management (server-side only), robust input validation to prevent cost attacks, defense mechanisms against prompt injection, and implementing per-user rate limiting. Essential reading for maintaining data privacy and system integrity in production environments.

A persistent memory kit designed for Claude AI agents. It maintains deep context across multiple sessions and projects using a two-layer architecture (hot cache and knowledge wiki). Features include safety hooks, multi-project context isolation, and a /close-day command for daily synthesis, ensuring agents remember complex information and continuously learn.

This guide details how to use sophisticated coding agents (such as Codex, Claude Code, or Pi) through a structured bash workflow. It provides methods for complex development tasks, including building new features, refactoring large codebases, and reviewing pull requests (PRs). Key best practices covered include managing pseudo-terminals (PTY), defining focused working directories (`workdir`), and executing tasks in the background for robust, multi-step automation.

This setup implements a pre-execution hook to safeguard code repositories by intercepting and blocking destructive Git operations (e.g., `git push`, `git reset --hard`, `git clean`). It prevents accidental or unauthorized data loss during automated code generation or tool use within AI environments, ensuring robust version control safety.

A deep dive into handling typed content blocks (text, image, tool_use, thinking, document) in LangChain 1.0. This skill standardizes multi-modal message composition, tool-call iteration, and complex content handling across providers like Claude, GPT-4o, and Gemini, solving key API discrepancies.

A comprehensive guide to advanced, production-ready LLM inference using LangChain 1.0. This skill addresses common pitfalls and bugs when integrating multiple providers (Claude, GPT-4o, Gemini), covering issues like structured output reliability, correct streaming token accounting, and robust handling of complex AIMessage content blocks. It teaches best practices for model initialization, provider routing, and version-safe code implementation.

This skill provides comprehensive guidance on correctly configuring Model Context Protocol (MCP) servers within Claude Code. It details the critical concepts of configuration scope (user vs. project) and outlines best practices to prevent context pollution across different coding sessions. Users learn how to safely add, remove, and clean up MCP settings using specific JSON files, ensuring a stable and efficient development environment.

This advanced skill is designed to generate high-quality, publication-ready academic illustrations and diagrams. It utilizes a sophisticated, multi-stage iterative workflow involving Claude for planning, layout optimization, and strict visual review, combined with a dedicated local Codex app-server bridge for native image rendering. The process ensures that generated figures meet the rigorous aesthetic and structural standards required for top-tier conferences and journals (e.g., CVPR, NeurIPS).

This advanced tool acts as a specialized prompt engineer, guiding users to create highly optimized, production-ready prompts for various AI models (LLMs, Midjourney, etc.). It enforces strict writing rules, guides detailed intent extraction (Task, Context, Constraints), and provides model-specific best practices (e.g., Claude vs. GPT-5.x) to maximize AI output quality and maintain consistency. Essential for professional content creators, developers, and researchers needing precise AI interaction.