Search Skills

Provides secure authentication and authorization patterns for login flows, JWT, OAuth 2.1, and role-based access control implementation.

Provides comprehensive pull request reviews using multiple specialized agents to ensure code quality and catch issues early.

Guides implementation of message queue patterns for asynchronous communication, pub/sub systems, and event-driven microservices using RabbitMQ, Redis Streams, and Kafka.

Automates analysis, evolution, and rollback of skills based on usage patterns to improve and maintain skill definitions efficiently.

Provides reusable patterns for implementing Progressive Web App features with Workbox 7.x, service workers, and offline-first strategies.

Provides multi-layered security validation for AI pipelines and LLM integrations, eliminating single points of failure.

Optimizes Core Web Vitals metrics (LCP, INP, CLS) with performance budgets and RUM for improved page speed and user experience.

Enables persistent semantic memory across user sessions for LLM applications, allowing recall of past interactions and context.

Collects test results, build outputs, coverage metrics, and exit codes to verify work completion during code reviews and deployments.

Guides structured brainstorming to refine ideas and explore alternatives before coding or implementation plans.

Provides implementation guidance for saga patterns in distributed systems, covering orchestration, choreography, and compensation strategies for multi-service transactions.

Guides implementation of fault tolerance patterns including circuit breakers, retry with exponential backoff, and bulkhead isolation for distributed systems and LLM integrations.

Optimizes LLM application costs through Redis-based semantic caching, reducing redundant API calls with vector similarity matching.

Provides WCAG 2.2 AA compliance patterns for web applications, enabling accessibility auditing and implementation.

Enables advanced pytest configurations with custom markers, plugins, hooks, and parallel execution for optimized test infrastructure and reusable test utilities.

Generates text embeddings for semantic search, similarity matching, and document analysis using vector representations.

Provides testing patterns for LLM-based applications, including mocking responses and validating structured outputs.

Enables structured LLM tool interactions through function schemas, execution loops, and external API integration for AI agents.

Automates quality assessment of LLM outputs using LLM-as-judge patterns and quality gates for AI application reliability.

Automates GitHub pull request creation with validation checks and intelligent description generation for streamlined code reviews.

Quickly undo commits, recover branches, and fix Git history using reflog operations to resolve common version control errors.

Interactive wizard for configuring OrchestKit settings, MCP servers, and plugin options to streamline infrastructure setup and management.

Automates coordination of multiple Claude Code instances across Git worktrees, preventing conflicts and managing file locks.

Analyzes error patterns and provides troubleshooting guidance for Claude Code sessions to resolve coding failures efficiently.