Skill UI

This skill enables Claude to run the load-balancer-tester plugin and validate traffic distribution, failover handling, sticky sessions, and health check behavior so teams can ensure high availability before deployment.

A comprehensive guide covering best practices for unit and integration testing, including Test-Driven Development (TDD) and Behavior-Driven Development (BDD). This guide details factory functions for creating reusable mock data and props, advanced mocking strategies for modules and hooks, and custom rendering utilities, ensuring tests are maintainable and reliable in React/TypeScript environments.

Document outlines testing strategies such as contract, snapshot, mutation, property-based, integration with containers, and disciplined test organization to help teams design reliable suites that cover behavior, API contracts, and invariants.

Automates Text To PDF workflows via Composio's Rube MCP, ensuring tool discovery, connection management, and schema-compliant execution for reliable PDF generation tasks.

Enables orchestrating Textcortex workflows through Rube MCP/Composio by discovering the latest tool schemas, ensuring connections stay active, and executing schema-compliant multi-tool calls for text generation and management tasks.

Automation workflow for The Odds API using Rube MCP via Composio, covering tool discovery, connection checks, execution patterns, pagination handling, and schema compliance so workflows stay reliable.

This comprehensive skill provides advanced architectural patterns for implementing robust API throttling and rate limiting policies. It covers critical concepts like concurrency limiting, priority queuing, circuit breakers, and adaptive throttling that adjust limits based on real-time backend health metrics (p95/p99 latency). Use this when designing resilient, scalable backend services that must protect themselves from overload and maintain stability under high load.

A comprehensive skill for structured software development life cycle (SDLC). It guides users through adaptive phases—Specify, Design, Tasks, and Execute—ensuring that every feature is built with traceable requirements, atomic tasks, and rigorous verification. Features include an independent Verifier, persistent decision logging, and a self-improving lessons layer to enhance future development quality. Ideal for complex, multi-component feature implementation.

Automates generating TorchServe deployment configurations with guided best practices for model serving, MLOps pipelines, inference, and production monitoring so ML deployment workflows stay consistent and reliable.

This skill provides comprehensive guidance for the entire lifecycle of Conductor tracks—the logical work units used to organize features, bugs, and refactors. It assists users in creating, reviewing, updating specifications (spec.md), developing plans (plan.md), and managing the status and metadata of tasks from initial conception through final completion, ensuring structured and traceable development processes.

Enables Claude to manage AI/ML model versions through the model-versioning-tracker plugin, automating logging, lineage tracking, performance summaries, and version retrieval whenever users request registry or deployment support.

Automates the end-to-end training of machine learning models by analyzing datasets, selecting suitable algorithms, tuning parameters, performing cross-validated training, and emitting performance metrics plus a saved model artifact.