Skill UI

Expert in designing and implementing advanced Retrieval-Augmented Generation (RAG) pipelines. This role focuses on optimizing the entire information retrieval process—from document chunking and embedding model selection to vector database architectures and hybrid search strategies. The goal is to bridge the gap between raw knowledge documents and accurate LLM understanding, drastically reducing hallucination and enhancing context relevance for enterprise applications.

This comprehensive checklist guides developers through the necessary steps to deploy a robust and reliable Grammarly API integration in a production environment. It covers critical aspects such as secure credential storage, rate limit handling, implementing text chunking, designing error resilience patterns (circuit breakers, retries), and establishing comprehensive monitoring and alerting systems to ensure high content quality and system uptime.

This guide provides production-ready patterns for integrating with the Grammarly API using both TypeScript and Python. It covers essential architectural aspects, including typed client implementation, robust token management (OAuth flow), and efficient text chunking for processing large documents. Use this when building scalable, reliable Grammarly-powered features into your application.

This guide provides advanced, deep debugging techniques for complex Figma REST API issues that resist standard error handling. It covers full network tracing (cURL), validating unexpected response shapes (TypeScript), measuring rate limits, and safely chunking large files. Use this when standard troubleshooting fails, or detailed evidence is required for support escalation.

A guide and toolkit for optimizing Grammarly API costs in large-scale applications. It addresses common cost overruns associated with high text volume by implementing strategies such as result caching, chunking long documents, sample-based scoring, and setting usage budget alerts. Use this when integrating Grammarly into enterprise workflows or managing billing for high-volume content analysis.

This skill guides the creation of technical documentation (such as RFCs, READMEs, PR descriptions, and architecture guides) that minimizes the mental effort required for the reader. It emphasizes structural patterns like 'Lead with the answer,' 'Chunking,' and 'Progressive disclosure' to ensure content is scannable, actionable, and easy to review, significantly reducing cognitive load for maintainers and contributors.

Split extracted text into chunks for LLM context windows or RAG ingestion. Supports character/token sizing, overlap, markdown/yaml/semantic chunkers, and inline or standalone usage via the chunk command.

Vexor CLI enables semantic file discovery within large repositories. Instead of manual browsing or exact text matching, it locates files based on intent, implementation, or definition. It supports various search modes like code-aware chunking and Markdown outlines, allowing developers to quickly find relevant code or documentation. Use it for locating entrypoints, config logic, or specific features efficiently.

Extract text, tables, metadata, and images from 107 document formats with Xberg APIs in Python, Node.js, Rust, or CLI. Covers installation, sync/async extraction, OCR, chunking, batch processing, and plugins.