Skill UI

Uses the Gemini API to autonomously plan, search, read, and synthesize detailed research reports with streaming status updates, structured outputs, and the ability to continue previous investigations for market analysis, technical reviews, or due diligence.

Automates Docsbot AI workflows through Rube MCP by discovering tools with RUBE_SEARCH_TOOLS, validating the docsbot_ai connection, and driving schema-compliant executions via RUBE_MULTI_EXECUTE_TOOL.

Automates Dreamstudio tasks through Rube MCP and Composio by discovering the latest tool schemas, validating active connections, and driving execution with RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL workflows.

A comprehensive guide for selecting and optimizing embedding models for advanced vector search and retrieval-augmented generation (RAG) applications. This guide covers model comparison, chunking strategies, dimension reduction techniques, and provides runnable Python templates for both OpenAI and local Sentence Transformer implementations.

This advanced workflow extends beyond basic search capabilities. It allows users to discover pages semantically similar to a given URL, retrieve detailed content, highlights, and summaries from known URLs (batch processing), and generate comprehensive, cited answers using AI. Ideal for deep academic research, competitive intelligence, and content enrichment pipelines.

This skill manages and refines search results obtained from Exa's neural search API. It provides comprehensive control over content extraction scope, allowing users to selectively retrieve metadata, highlights, full text, or structured summaries. Key features include implementing result caching with TTL, deduplicating citations, and crucial token budget management, ensuring the retrieved context fits within LLM context window limits for robust RAG pipelines.

Leverages the Exa API for semantic/embeddings search, discovering similar content, or filtering by categories like companies, people, and research papers, making research and knowledge retrieval more targeted.

FAISS (Facebook AI Similarity Search) is a library designed for efficient similarity search and clustering of dense vectors. It supports indexing and searching on billions of vectors at scale, featuring GPU acceleration and multiple index types (Flat, IVF, HNSW, PQ) to balance speed and accuracy. It is essential for building high-performance, large-scale applications requiring fast k-NN retrieval or pure vector similarity matching, especially in fields like RAG and recommendation systems.

Automates FlowiseAI workflows by orchestrating Rube MCP and Composio tools; always searches current tool schemas, validates active Flowiseai connections, and executes schema-compliant multi-tool calls with session reuse.

Automate Google Photos workflows through Rube MCP (Composio) to list and manage albums, upload or batch-create media, search items, and organize albums using the provided toolkit tools and schema-aware commands.

A comprehensive guide to implementing advanced LLM patterns using the Groq API. This workflow demonstrates how to handle chat completions, robust tool/function calling for integrating external services (like weather or search), and enforcing structured data output using JSON mode and strict schemas. Ideal for building real-time, production-grade AI features.

This skill provides structured patterns for combining vector similarity search with traditional keyword-based search. It is essential for building advanced Retrieval-Augmented Generation (RAG) systems, sophisticated search engines, or any retrieval task requiring high recall. Use this when pure semantic understanding is insufficient, and precise matching of specific terms (like names or codes) is necessary.