RAG Pipeline Optimization with Claude
Design and optimize RAG systems for production-grade accuracy and performance
What You Can Do
You can systematically evaluate and improve your RAG pipelines using Claude as a design partner. You'll analyze retrieval quality, identify bottlenecks in your embedding and chunking strategies, and receive actionable recommendations to reduce hallucinations and improve context relevance. By the end, you'll have a data-driven optimization plan tailored to your specific use case and performance metrics.
Features
Analyze precision, recall, and relevance scores across your document chunks
Rewrite and decompose queries for better vector search results
Find the optimal granularity for your domain and retrieval patterns
Compare embedding strategies and select models for your performance needs
Identify gaps between retrieved context and model outputs, with concrete fixes
Design effective prompts that balance context length with accuracy
Evaluate semantic distance calculations and similarity thresholds
Craft system prompts and instructions that minimize out-of-context outputs
Example Output
RAG Evaluation Report
-
✅ Retrieval Quality Score: 78/100
-
Precision (correct docs returned): 82%
-
Recall (relevant docs captured): 74%
-
Mean reciprocal rank: 0.71
-
❌ Key Issues Identified
-
Chunk size (512 tokens) too small for multi-step reasoning queries
-
Embedding model (text-embedding-3-small) loses semantic nuance for domain terminology
-
Query rewriting not active; queries like "What does the warranty cover?" map to irrelevant sections
-
💡 Optimization Plan
- Increase chunk size to 1024 tokens with 200-token overlap
- Migrate to text-embedding-3-large with domain-specific fine-tuning
- Add query decomposition: break multi-part questions into sub-queries
- Set similarity threshold to 0.75 (currently 0.5) to reduce noise
Expected Impact: Precision +12%, Recall +8%, hallucination rate -35%
What's Included
- SKILL.md: Full RAG optimization workflow with decision trees and evaluation frameworks
- RAG Quality Checklist: Evaluation criteria for retrieval, ranking, and context relevance
- Query Optimization Template: Strategies for decomposition, rewriting, and intent detection
- Embedding Strategy Decision Tree: Select models, chunk sizes, and vector similarity thresholds
- Performance Metrics Tracker: Template to log precision, recall, MRR, and latency across iterations
- Hallucination Root-Cause Analyzer: Worksheet to identify when and why the model deviates from context
Who It's For
- ML Engineers building and tuning RAG systems for production
- Data Engineers designing document ingestion and vector storage pipelines
- LLM Application Developers integrating retrieval into chat and search products
- AI Product Managers optimizing RAG performance for user-facing features
- Prompt Engineers evaluating context quality and reducing hallucinations
Best For
- Evaluating retrieval quality and identifying bottlenecks
- Optimizing chunk size, overlap, and embedding strategies
- Designing multi-turn RAG workflows with query rewriting
- Reducing hallucinations by improving context relevance
- Benchmarking RAG performance metrics (precision, recall, MRR)
You might also like
You can design statistically valid experiments with proper power analysis, choose the right statistical tests for your data type, analyze results while controlling for multiple comparisons, and generate publication-ready reports with accurate interpretation of findings. Claude helps you avoid common statistical pitfalls and ensures your experimental claims are well-supported by evidence.
by moonwell-fi
This skill automatically documents your entire analytics infrastructure by analyzing data sources, transformations, and outputs. You'll generate production-ready data dictionaries with field definitions, lineage maps showing data flow across systems, and transformation documentation that explains logic and dependencies. Save weeks of manual documentation work while keeping your analytics stack discoverable as it evolves.
by moonwell-fi
You'll systematically diagnose data quality problems by developing structured root cause analysis frameworks, calculating the true business impact, and creating reproducible validation tests. This skill walks you through hypothesis-driven investigation, data lineage analysis, and remediation planning — turning data issues into documented fixes and preventive measures.
by moonwell-fi
You'll build comprehensive data quality test suites that validate transformations, detect anomalies, and document standards across your dbt and SQL pipelines. This skill generates production-ready test configurations, anomaly detection protocols, and validation rules that catch data issues before they impact analytics.
by moonwell-fi
You can rapidly compile, organize, and format disparate health economic evidence—from clinical trials to cost-effectiveness analyses—into structured, regulatory-compliant dossiers. This skill maps your evidence to specific payer and HTA requirements, automatically generates evidence hierarchies, and produces submission-ready dossier outlines with formatting that meets regulatory standards for NICE, EUnetHTA, and other major bodies.
by moonwell-fi
You can structure comprehensive health technology assessments (HTAs) that organize clinical evidence, economic analyses, and regulatory considerations into evidence-based coverage recommendations. This skill helps you synthesize clinical trial data, health economic models, and real-world evidence into clear, defensible payer coverage determinations. You'll generate professional HTA reports that align with major frameworks like ICER, CADTH, and NICE standards.
by moonwell-fi
This skill detects your project framework (Vite, Next.js, plain Node, or monorepo) and automatically configures agent-tail to pipe dev server and browser console logs into unified log files. You'll get a proposed configuration tailored to your setup, install agent-tail with the correct plugins, and have logs immediately available for AI agents to consume and analyze.
by moonwell-fi
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