Data Science & ML Agent Skills

Semantic Embeddings & Vector Search

Converts text into high-dimensional vector representations for semantic search, document similarity, and RAG pipelines.

Alternative Agent Frameworks

Provides implementation patterns and comparison guides for multi-agent orchestration frameworks including CrewAI, OpenAI Agents SDK, and Microsoft Agent Framework.

LangGraph Conditional Routing

Implements dynamic workflow routing, retry loops, and semantic branching for LangGraph-based AI agents.

Golden Dataset Curation

Curates high-quality evaluation datasets for AI models using multi-agent validation and automated quality scoring.

LangGraph Parallel Execution

Implements high-performance parallel execution patterns for LangGraph workflows using fan-out/fan-in and map-reduce strategies.

Contextual Retrieval for RAG

Implements Anthropic's contextual retrieval technique to improve RAG performance by prepending situational metadata to document chunks.

Multimodal RAG Patterns

Implements advanced retrieval-augmented generation systems that integrate text and image data for hybrid search and visual question answering.

RAG Reranking Patterns

Enhances search precision in RAG pipelines by re-scoring retrieved documents using high-accuracy Cross-Encoders and LLM relevance patterns.

HyDE Semantic Retrieval

Enhances RAG retrieval quality by generating and embedding hypothetical answer documents to bridge vocabulary gaps between queries and data.

Semantic Caching

Optimizes LLM performance and reduces API costs by implementing Redis-powered vector similarity caching.

Vision Language Model Integration

Integrates advanced vision-language models for image analysis, document understanding, and multimodal reasoning within Claude Code.

Fine-Tuning & Customization

Simplifies Large Language Model fine-tuning and alignment using parameter-efficient techniques like LoRA, QLoRA, and DPO.

Golden Dataset Validator

Validates AI evaluation datasets for schema compliance, content integrity, and duplicate detection to ensure high-quality benchmarking.

Mem0 Long-Term Memory

Persists semantic context and project decisions across multiple Claude Code sessions using Mem0.

Golden Dataset Quality Validator

Ensures high-quality AI evaluation datasets by performing automated schema validation, duplicate detection, and coverage analysis.

LLM Function Calling & Tool Use

Enables LLMs to interact with external tools and return structured data through standardized function calling patterns and strict schemas.

LLM Output Evaluation & Quality Assurance

Implements advanced LLM-as-judge patterns and RAGAS metrics to evaluate AI output quality and detect hallucinations.

High-Performance Inference

Optimizes Large Language Model inference for production environments using vLLM, advanced quantization, and speculative decoding.

LangGraph Checkpointing & Persistence

Manages fault-tolerant workflow persistence and state recovery for LangGraph AI agents.

RAG Retrieval Patterns

Implements production-ready Retrieval-Augmented Generation patterns to ground AI responses in factual data and minimize hallucinations.

Golden Dataset Curator

Manages the multi-agent curation of high-quality training and testing datasets with automated quality scoring and bias detection.

LLM Evaluation & Quality Assessment

Implements automated quality gates, LLM-as-judge patterns, and RAGAS metrics to ensure reliable and grounded AI outputs.

High-Performance LLM Inference

Optimizes Large Language Model inference for production environments using vLLM, advanced quantization, and speculative decoding techniques.

RAG Retrieval Patterns

Implements robust Retrieval-Augmented Generation (RAG) patterns to ground LLM responses with accurate, cited, and validated external data.

Alternative Agent Frameworks

Implement and compare multi-agent orchestration frameworks like CrewAI, OpenAI Agents SDK, and Microsoft Agent Framework for specialized AI workflows.

Query Decomposition

Breaks down complex search queries into independent sub-concepts to improve retrieval accuracy and coverage in RAG systems.

Golden Dataset Curator

Manages the automated curation and multi-agent validation of high-quality datasets for LLM evaluation.

LangGraph Human-in-the-Loop

Implement robust human-in-the-loop approval workflows, manual review gates, and interactive agent supervision patterns in LangGraph.

Query Decomposition

Decomposes complex, multi-concept queries into independent sub-topics to improve RAG retrieval accuracy and coverage.

CRAN Submission Preparation

Automates mandatory checks and fixes for R packages to ensure compliance with CRAN's strict ad-hoc submission requirements.