Search Skills

Enables Redis-based semantic caching for LLM applications, optimizing costs through vector similarity and response caching.

Tracks LLM cost savings from caching via Langfuse, monitoring cache effectiveness and attributing costs to agents in multi-agent AI systems.

Enables consumer-driven contract testing for API compatibility, ensuring microservice integrations remain stable and preventing breaking changes.

Provides API rate limiting implementations using token bucket, sliding window, and Redis for request throttling and abuse protection.

Enables LLMs to interact with external tools via function calling, including schema definition and structured output generation.

Optimizes LLM costs by caching prompts for Claude and OpenAI, reducing token usage for repeated system prompts and prefixes.

Optimizes images in Next.js 15 using AVIF/WebP formats, blur placeholders, and responsive sizing for improved performance.

Automates browser testing for end-to-end validation of user journeys across multiple browsers using Playwright.

Configures CI/CD pipelines, containerizes applications, deploys to Kubernetes, and manages infrastructure as code with Terraform and Docker.

Enhances RAG systems by implementing hybrid BM25 and vector search to maintain context and reduce retrieval failures in AI models.

Provides production-ready implementations of fault tolerance patterns including circuit breakers, retry with exponential backoff, and bulkhead isolation for distributed systems and LLM integrations.

Optimizes LLM inference latency and throughput using vLLM, quantization, and speculative decoding for efficient deployment.

Provides Nygard-format templates for documenting software architecture decisions in Architecture Decision Records (ADRs).

Enables end-to-end type safety in TypeScript applications using Zod, tRPC, and Prisma for schema validation and input handling.

Manages golden datasets for AI/ML evaluation, ensuring integrity via backup, restore, and validation to prevent data loss.

Provides utilities for implementing scroll-driven animations using CSS ScrollTimeline and ViewTimeline, enabling parallax effects and smooth scroll-linked animations.

Manages API versioning through path, header, and content negotiation to handle migrations, breaking changes, and backward compatibility.

Automates security scanning of dependencies and code using tools like npm audit, pip-audit, and Semgrep, with CI/CD integration.

Provides essential Git workflow patterns including branching strategies, atomic commits, and history recovery for clean version control.

Provides advanced Vite 7+ configuration for environment setup, plugin development, SSR, and build optimization in frontend projects.

Enables implementation of clean architecture using SOLID, hexagonal patterns, and DDD for decoupled, testable backend systems.

Automates the creation and management of stacked pull requests for efficient code review and development of large features.

Adds and validates documents to a golden dataset for AI/ML testing and training using multi-agent validation to ensure data quality.

Validates golden datasets for AI evaluation through schema checks, duplicate detection, and coverage analysis to ensure data integrity.