giuseppe-trisciuoglio/developer-kit
Overview
This skill provides practical patterns and a developer-ready playbook for building Retrieval-Augmented Generation (RAG) systems that ground LLM responses with external knowledge sources. It covers vector store selection, embedding model choices, document processing, retrieval strategies, and end-to-end RAG pipelines for production and local development. Use it to reduce hallucinations and deliver factual, source-cited answers from proprietary or multi-source knowledge bases.
How this skill works
The skill guides you to ingest documents, split them into chunks, generate embeddings, and store those vectors with metadata in a vector database. It describes retrieval strategies (dense, sparse, hybrid), reranking and filtering techniques, and how to wire a retriever into an LLM prompt template with chat memory and grounding checks. It also includes evaluation metrics and optimization steps for precision, latency, and faithfulness.
When to use it
- Building Q&A systems over proprietary documents or manuals
- Creating chatbots that must provide current, factual information
- Implementing semantic search with natural language queries
- Reducing hallucinations by grounding responses in retrieved sources
- Combining multiple knowledge sources (web, DB, docs) for unified answers
Best practices
- Choose a vector store that matches scale and deployment needs (Pinecone/Milvus for production, Chroma/FAISS for local)
- Preprocess and clean documents, add useful metadata for filtering and context
- Use 500–1000 token chunks with 10–20% overlap, then test variations for your corpus
- Start retrieval with a higher k (10–20) and apply reranking or filtering to improve precision
- Cache embeddings, batch ingestions, and monitor query latency and resource usage
Example use cases
- Document Q&A assistant that answers policy or support questions with citations
- Conversational product assistant that keeps context across multi-turn sessions
- Research tool that merges results from document, database, and web retrievers and reranks them
- Knowledge management system that exposes domain-specific content via semantic search
- Compliance auditor that filters and retrieves documents by metadata and date ranges
FAQ
Use a managed, scalable option like Pinecone or Milvus for production; choose Weaviate or Qdrant if you need open-source features and advanced filtering.
How do I reduce hallucinations in RAG?
Emphasize grounding in prompts, add verification steps, include confidence scores, and use reranking or cross-encoder validation to ensure answers reflect retrieved documents.
50 skills
This skill helps design and implement retrieval-augmented generation systems with vector databases, embeddings, and grounding for knowledge-grounded AI.
This skill helps you implement fault tolerance in Spring Boot apps using Resilience4j by adding circuit breakers, retries, rate limiters, bulkheads, and
This skill provides patterns for unit testing JSON serialization and deserialization with Jackson and JsonTest to validate mappings and formats.
This skill streamlines Spring Boot dependency injection by enforcing constructor-first patterns, optional collaborators, and explicit bean configuration to
This skill helps you create production-ready S3 infrastructure with CloudFormation templates, including buckets, policies, versioning, and lifecycle rules.
This skill helps Spring Boot developers integrate LangChain4j with declarative AI services and auto-configuration for production-grade AI apps.
This skill provides patterns for unit testing mappers and converters to verify accurate data transformations between DTOs and domain objects.
This skill enables building agentic applications by defining tools and function calls with LangChain4j, enabling real-time API access and external integrations.
This skill teaches practical Amazon S3 operations with AWS SDK for Java 2.x, enabling efficient bucket management, object handling, and presigned URLs.
This skill helps you model production-ready ElastiCache infrastructure with CloudFormation, covering clusters, replication groups, subnet and parameter groups.
This skill provides REST API design standards for Spring Boot, guiding endpoints, DTOs, validation, error handling, pagination, security headers, and HATEOAS.
This skill guides unit testing of Spring Cache annotations using in-memory caches to verify hits, misses, eviction, and key generation.
This skill provides CloudFormation patterns for AWS Bedrock resources to deploy agents, knowledge bases, data sources, guardrails, prompts, flows, and
This skill helps you design production-ready AWS CloudFormation VPC templates with modular, reusable subnets, routes, and cross-stack references for scalable
This skill guides you to test Spring ApplicationEvent publishing and listeners with JUnit, Mockito, and AssertJ for fast, reliable event-driven tests.
This skill generates production-ready TypeScript documentation with API references, ADRs, and runnable examples for frameworks like NestJS, React, and Angular.
This skill helps you implement Tailwind CSS development patterns for mobile-first, responsive layouts, design tokens, and component reuse to speed up UI work.
This skill guides you through setting up shadcn/ui, installing components, and building accessible, Tailwind-styled React UI patterns.
This skill creates production-ready AWS architecture diagrams in draw.io XML using official AWS icons, enabling clear infrastructure visuals.
This skill helps you implement Clean Architecture, Hexagonal Architecture and DDD in PHP/Symfony, ensuring testable, framework-agnostic domain logic.
This skill helps you leverage React 19 patterns including Server Components, Actions, use(), and concurrent features to build scalable, high-performance
This skill helps you implement AWS CloudFormation IAM resources with least privilege, cross-account access, and structured templates for secure infrastructure.
This skill helps you unit test REST controllers with MockMvc by isolating the web layer and validating requests, responses, and errors.
This skill enables efficient DynamoDB usage with AWS SDK for Java 2.x, delivering type-safe operations and Spring Boot integration.
This skill guides you in writing parameterized unit tests with JUnit 5 using various sources to cover multiple scenarios efficiently.
This skill implements production-ready JWT authentication and authorization for Spring Boot 3.5.x, enabling stateless security and RBAC with Spring Security.
This skill helps you configure Spring Boot Actuator for production-grade monitoring, health checks, and secure, observable JVM services.
This skill helps you optimize retrieval by selecting and tuning chunking strategies for RAG systems and large documents.
This skill helps you implement feature-aligned CRUD services in Spring Boot 3.5+, aligning aggregates, repositories, and controllers with clean DTOs.
This skill helps you validate exception handling in Spring controllers by testing @ExceptionHandler and @ControllerAdvice with MockMvc for precise error
This skill provides testing strategies for LangChain4J applications, enabling reliable unit, integration, and end-to-end tests with mocks and Testcontainers.
This skill helps you implement AWS messaging with SQS and SNS using Java SDK 2.x, covering queues, topics, DLQ, and Spring Boot patterns.
This skill helps you validate @ConfigurationProperties bindings with ApplicationContextRunner, ensuring proper binding, validation, defaults, profiles, and
This skill guides building robust Spring Boot test suites with unit, slice, and integration patterns using Testcontainers and MockMvc.
This skill helps you apply comprehensive unit-test boundary patterns, covering min/max values, nulls, empties, precision, and edge cases across Java/Python
This skill provides reusable AWS CloudFormation patterns for EC2, security groups, IAM roles, and ALB configurations to speed infrastructure as code.
This skill helps you design production-ready AWS CloudFormation patterns for RDS databases, including instances, clusters, subnets, parameter groups, and
This skill helps you securely manage secrets with AWS Secrets Manager using Java SDK v2, including storing, retrieving, rotating, and Spring Boot integration.
This skill helps Java developers integrate Amazon Bedrock patterns with AWS SDK 2.x, enabling model listing, invocation, streaming, and Spring Boot integration.
This skill helps you configure AWS SDK for Java 2.x with best practices for clients, authentication, timeouts, and error handling.
This skill helps you define production CloudFront distributions with CloudFormation, multiple origins, caching, security headers, and cross-stack references.
This skill helps you create secure AWS CloudFormation templates by applying best practices for encryption, secrets management, and defense-in-depth.
This skill helps you build declarative, type-safe AI services with LangChain4j in Java, enabling memory, tool integration, and structured outputs.
This skill helps you unit-test Jakarta Bean Validation with patterns and examples for built-in constraints and custom validators.
This skill provides patterns to integrate SpringDoc OpenAPI 3.0 with Spring Boot 3.x, generating comprehensive REST API documentation and Swagger UI.
This skill provides AWS CloudFormation patterns for ECS clusters, services, task definitions, and blue/green deployments to simplify infrastructure as code.
This skill guides deploying ECS tasks and services via GitHub Actions with CloudFormation, enabling secure OIDC authentication and multi-environment pipelines.
This skill helps you enable and manage Spring Cache across services, improving performance with @Cacheable, TTLs, and eviction strategies.
This skill helps you implement production-grade AWS CloudWatch monitoring with CloudFormation templates, covering metrics, alarms, dashboards, logs, and
This skill helps you manage AWS RDS resources using the Java v2 SDK, covering instances, snapshots, parameter groups, backups, and monitoring.
