Skill UI

This skill provides foundational security patterns and implementation guides for building AI voice agents and automating phone call workflows using Retell AI. It covers essential SDK usage (TypeScript), agent listing, and critical error handling (e.g., 401 Unauthorized, 429 Rate Limit) when integrating Retell into voice or telephony applications.

Conducts detailed accessibility audits for web apps via the accessibility-test-scanner plugin, verifying WCAG 2.1/2.2 compliance, ARIA usage, keyboard navigation, and screen reader compatibility while providing remediation guidance when accessibility or compliance checks are requested.

A comprehensive, model-agnostic toolkit for advanced LLM development. It enables iterative prompt optimization through static analysis (token usage, clarity), measures critical RAG metrics (relevance, faithfulness, coverage), and validates complex agent workflows and configurations. Essential for rigorous LLM quality assurance and cost management.

This framework enforces organizational governance and policy guardrails for Sentry usage. It standardizes configuration across services, mandatorily scrubbing PII, enforcing naming conventions, and managing trace rate caps based on service criticality. It integrates into CI/CD to prevent compliance drift and ensure adherence to standards like GDPR and HIPAA.

Serve production-grade LLM APIs with vLLM, leveraging PagedAttention, continuous batching, quantization, and tensor parallelism to maximize throughput while keeping latency, GPU usage, and scalability under control for OpenAI-compatible deployments.

A specialized methodology for reviewing APIs, configuration schemas, and interfaces to identify 'footguns'—design choices where the path of least resistance leads to insecurity. This analysis focuses on making secure usage the default, covering topics like dangerous defaults, primitive vs. semantic type safety, and insecure algorithm selection. It is crucial for architects and reviewers to prevent developer misuse at the design level.

This skill guides the mastery of smart contract security best practices for Solidity. It is essential for writing robust, secure, and efficient contracts, auditing existing code for common vulnerabilities (such as reentrancy, overflow, and access control issues), and implementing secure DeFi protocols. It focuses on preventing common attack vectors while optimizing gas usage.

A comprehensive guide for optimizing costs when integrating the Speak API. This skill covers usage monitoring, selecting optimal API tiers, and implementing efficient audio processing pipelines. It is essential for developers managing language learning platform operations to ensure cost efficiency while maintaining high performance.

This skill guides the configuration of Speak for enterprise environments, such as schools and large organizations. It covers implementing Role-Based Access Control (RBAC), setting up Single Sign-On (SSO), managing diverse roles (teacher/student), handling class management, and establishing usage reporting. This setup is essential for deploying a secure, scalable language learning platform tailored for institutional use.

This skill provides comprehensive observability for the Speak language learning platform. It monitors critical metrics such as API health status, assessment latency, session usage, and detailed pronunciation score distributions. It is essential for developers implementing robust, production-grade monitoring systems and managing large-scale language learning operations.

A placeholder skill definition that outlines where to insert a descriptive summary and usage guidance so Claude knows when to call this template.

Tracks CPU, memory, disk/network I/O, DB connections, and threads via the resource-usage-tracker plugin to reveal performance bottlenecks, recommend right-sizing, and guide cost-saving actions.