Rag Pipeline Builder
Design and optimize end-to-end RAG pipelines with intelligent document retrieval
What You Can Do
You'll design complete RAG architectures from ingestion through inference, making strategic decisions on chunking strategies, embedding models, vector database selection, and retrieval tuning. This skill guides you through all five core pipeline phases—document preprocessing, semantic embedding, vector storage, ranking optimization, and context window assembly—ensuring your system balances accuracy, latency, and cost for domain-specific knowledge retrieval at scale.
Features
Design semantic-aware splitting with overlap, handling different document types (PDFs, markdown, structured data)
Choose between dense embeddings (OpenAI, Cohere, open-source) based on cost, latency, and domain fit
Evaluate and configure PostgreSQL pgvector, Pinecone, Weaviate, Chroma, or Milvus for scalable retrieval
Implement hybrid search, BM25 + semantic fusion, re-ranking, and metadata filtering to maximize relevance
Intelligently pack retrieved chunks within token limits while preserving semantic coherence
Deploy via LangChain, LlamaIndex, or custom Python implementations with minimal scaffolding
Design metrics for retrieval quality (NDCG, MRR) and end-to-end answer accuracy
Example Output
Example 1: E-commerce Product Support RAG
- Chunking: 256-token sections from product manuals with 64-token overlap, preserving section headers
- Embedding: OpenAI text-embedding-3-small for cost efficiency
- Vector Store: Pinecone with product category metadata filtering
- Retrieval: Hybrid (BM25 + semantic) with MMR reranking for diversity
- Output: Customer service bot retrieving exact product specs with 94% accuracy on FAQ queries
Example 2: Legal Document Discovery System
- Chunking: Clause-aware segmentation respecting legal document structure
- Embedding: Self-hosted sentence-transformers for data sovereignty
- Vector Store: PostgreSQL pgvector for on-premise deployment
- Retrieval: Dense passage retrieval + legal metadata filters (document type, jurisdiction, date range)
- Output: Paralegal tool surfacing relevant precedents in 200ms with full citation trails
What's Included
- RAG Pipeline Builder SKILL.md: Complete instruction framework for designing RAG systems
- Chunking Decision Matrix: Comparison of splitting strategies (semantic, fixed-size, recursive) with trade-offs
- Vector Store Comparison Checklist: Evaluation criteria for 6+ vector databases (cost, latency, scalability)
- Retrieval Tuning Workflow: Step-by-step process for testing embeddings, ranking strategies, and hybrid search
- Context Packing Template: Code patterns for intelligent document assembly within token windows
- RAG Evaluation Framework: Metrics and benchmarking approach for retrieval quality
Who It's For
- AI/ML Engineers — Building production RAG systems for customer-facing applications
- Data Scientists — Designing knowledge retrieval architectures for proprietary datasets
- LLM Product Managers — Making technical decisions on embedding and vector storage stack
- Enterprise Architects — Planning document intelligence solutions across organizational knowledge bases
- Prompt Engineers — Optimizing retrieval performance to ground AI responses in domain expertise
Best For
- Designing document-grounded Q&A systems (customer support, FAQ automation)
- Building legal/compliance document discovery tools
- Creating research or scientific paper recommendation engines
- Architecting enterprise knowledge management systems
- Optimizing existing RAG pipelines for speed, cost, or accuracy
- Evaluating and selecting appropriate vector databases and embedding models
You might also like
This skill helps you systematically diagnose failures in distributed ML training and serving infrastructure. You provide system logs, metrics, and error traces, and Claude performs structured root-cause analysis to identify the underlying issue—whether it's resource exhaustion, distributed system deadlock, data pipeline corruption, or model serving misconfiguration. You get a detailed diagnosis with remediation steps ranked by likelihood and implementation effort.
by moonwell-fi
You describe your data and insights to Claude, and it designs custom charts, writes production-ready rendering code, and optimizes every visual detail for clarity and impact. Whether you're building dashboards, infographics, or presentation decks, Claude translates raw datasets into stories that resonate with your audience.
by moonwell-fi
You can systematically diagnose why your RAG system isn't returning relevant results and identify specific misalignments between queries and context. This skill walks you through analyzing retrieval quality, scoring context relevance, and optimizing prompt-retrieval alignment to improve your RAG accuracy. You'll get concrete, actionable recommendations for fixing bottlenecks in your pipeline.
by moonwell-fi
You'll handle difficult guest conversations with structured communication templates that de-escalate tension while protecting your property. Generate professional damage assessments, complaint responses, and resolution protocols that document interactions clearly and mitigate liability. Create personalized communication strategies tailored to each guest situation, from minor maintenance requests to serious damage claims.
by moonwell-fi
You can create well-structured semantic layer specifications that define business metrics, dimensions, and relationships from your raw data schemas. This skill validates your semantic layer design for consistency, identifies naming issues, detects redundancy, and generates comprehensive documentation and data dictionaries that keep your entire team aligned.
by moonwell-fi
Debug retrieval failures, optimize chunking strategies, and validate answer accuracy across different RAG configurations. You can systematically test embedding models, chunk sizes, query expansion techniques, and reranking parameters to maximize your pipeline's performance. This skill helps you measure the impact of changes and identify which retrieval bottlenecks are hurting your system most.
by skillslib
Systematically evaluate your Claude prompts using quantitative scoring frameworks to identify weaknesses in clarity, task alignment, and output quality. You'll receive detailed optimization recommendations with A/B testing guidance to improve prompt effectiveness and consistency across different use cases and input variations.
by moonwell-fi
This skill transforms high-level feature requests into actionable implementation plans by conducting deep requirement interviews, analyzing existing codebases (or planning greenfield projects), and producing comprehensive handoff documents. It distinguishes between brownfield development (with existing code to integrate) and greenfield projects (starting from scratch), ensuring your technical strategy accounts for your actual constraints and patterns.
by moonwell-fi