LlamaIndex plugins

Build production-grade LLM applications with patterns for RAG pipelines, agent architectures, prompt caching, context window management, and observability via Langfuse, integrating Anthropic, OpenAI, LangChain, and LlamaIndex toolchains.

Explain machine learning model predictions using SHAP, LIME, and feature importance to identify influential features and debug behavior. Generate production-ready AI/ML code from context, including validation, error handling, performance metrics, insights, artifacts, and documentation.

Manage the full lifecycle of UiPath automation projects from within Claude Code — build, deploy, and debug RPA workflows, agents, coded apps, integration connectors, and governance policies using CLI commands directly in the chat interface.

Manage the full AI/ML lifecycle on DataRobot: design and deploy AI agents, train models, engineer features, set up CI/CD pipelines, make predictions with explanations, monitor model performance and drift, and instrument external agents with OpenTelemetry.

Add persistent memory and personalization to AI applications with semantic search, guided memory recall, and automatic context management for Claude workflows.

Add Opik observability to LLM applications: auto-detect frameworks, trace execution flows, evaluate agent reliability, and monitor production performance with session telemetry controls for Claude Code.

Build production-grade LLM apps in Python: implement RAG pipelines with embeddings and hybrid search, design LangChain/LangGraph agents, optimize prompts, tune vector indexes, and evaluate performance using AI agents, skills, and commands for architecture, code gen, and benchmarking.

Automate Brazilian judicial workflows: analyze civil/criminal processes, draft decisions, calculate CPC/CPP deadlines, download PDF case files from PJe courts, extract text via OCR, search CJF jurisprudence, and generate stylized procedural reports in DOCX/PDF.

Build production-ready LLM applications by delegating to expert AI agents that engineer prompts, manage dynamic contexts with vector DBs and knowledge graphs, optimize single and multi-agent performance, and orchestrate RAG, multimodal, and enterprise AI workflows.

Skill-dev enables developers to author, test, and optimize Claude Code skills, agents, and MCP servers using prompt engineering best practices, Anthropic API integration, and context-window-efficient patterns.

Convert docs, repos, PDFs, videos, and more into AI-ready skill packages for LLM platforms like Claude, OpenAI, and Gemini, with auto-detection of source types and configurable preset levels.