Skill UI

This guide provides comprehensive instructions for installing and configuring the official Anthropic SDK for both Python and TypeScript. It covers setting up the necessary environment variables, managing API keys securely, and verifying the connection to the Claude Messages API endpoint. Essential for all new Claude API integrations.

This module provides comprehensive observability for Anthropic's Claude API integrations. It enables the tracking of critical operational metrics including latency, token usage (input/output), estimated API costs, and error rates. Use it to set up structured logging and Prometheus metrics for robust monitoring and alerting, ensuring reliable and cost-effective AI application deployments.

This comprehensive skill provides multi-layered guardrails for integrating with LLMs like Claude. It enforces security and compliance by implementing input validation (PII detection, length checks), system prompt restriction (scope control, safety rules), output filtering (preventing sensitive data leakage), cost governance, and model access policies. Ideal for building secure, robust, and governed AI applications.

A comprehensive checklist for deploying Claude API integrations to a production environment. It covers essential best practices for reliability, observability, and cost control, including authentication procedures, advanced error handling, rate limit management, health check implementation, and infrastructure deployment strategies (e.g., canary releases) to ensure a smooth and stable launch.

Implements robust rate limiting, backoff logic, and quota management for the Anthropic Claude API. It handles 429 errors and optimizes request throughput by managing Requests Per Minute (RPM), Input Tokens Per Minute (ITPM), and Output Tokens Per Minute (OTPM). This skill provides advanced strategies including SDK retries, custom header awareness, queue-based throttling, and batch processing for stable, high-throughput production applications.

A comprehensive guide for building applications with Claude, ensuring responsible data handling. This skill covers critical patterns such as PII redaction (stripping sensitive data like emails, phone numbers, and card numbers), optimizing the 200K token context window through conversation trimming, and implementing best practices for data retention and privacy compliance when interacting with the Anthropic API.

This skill provides comprehensive guides for deploying stateless, serverless API wrappers powered by Claude (Anthropic). It details how to integrate and stream responses from the Messages API across major cloud environments, including Vercel Edge Functions, Fly.io, and Google Cloud Run. It is essential for productionizing AI applications that require robust secret management, scalable infrastructure, and real-time streaming capabilities.

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.

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 skill provides comprehensive diagnosis and optimization for agent skill libraries. By analyzing historical session transcripts from platforms like Claude Code and Codex, alongside static skill file checks, it scores each skill across 8 dimensions. It identifies issues such as low trigger rates, poor post-invocation user reaction, and incomplete workflow execution, generating a prioritized report (P0/P1/P2) to significantly improve the agent's overall performance and reliability.

This tool functions as a Command Line Interface (CLI) alias for implementing the specific 'pua:mama' protocol within advanced coding models like Codex or Claude Code. It loads and enforces a structured 'mama skill/protocol,' maintaining rigorous verification standards while adjusting the visible narrative style to a specific 'Chinese-mom nagging mode.' It manages configuration by interacting with `~/.pua/config.json`, ensuring existing user fields are preserved.