Skill UI

Configure and select AI models inside Cursor by reviewing available providers, matching models to task needs, setting defaults, and managing per-conversation choices while keeping costs efficient.

Guides ML engineers through the Databricks secondary workflow that links Feature Store engineering, MLflow experiment tracking, model registry versioning, and serving so production-grade models can be trained and deployed.

Provides a workflow for automating Deepgram operations through Composio's toolkit using the Rube MCP bridge, covering prerequisites, tool discovery, connection checks, executions, and handling schema and pagination details.

Provides a minimal Deepgram transcription sample covering client initialization, URL/local audio transcription, and error handling tips so you can test setups or learn API basics quickly.

Provides a reference architecture for building scalable Deepgram transcription systems covering sync API, async queue, real-time streaming, hybrid routing and multi-region deployment.

Defines production-ready Deepgram SDK usage for TypeScript and Python, covering pre-recorded transcription, live streaming, diarization, multi-language handling, and error responses to guide integrations and team standards.

Guides securing Deepgram API integrations: storing keys safely, scoping permissions, rotating secrets, encrypting transcripts, and logging audits.

Guides automated distributed training setups with step-by-step practices, production-ready configs, and validation checks for ML training workflows.

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.

Provides interpretable explanations for ML predictions using SHAP, LIME, and other techniques, helping debug model behavior, highlight feature importance, and communicate fairness insights to stakeholders.

This skill provides capabilities for bidirectional audio processing using fal.ai models. It supports Text-to-Speech (TTS), converting written text into natural-sounding speech, and Speech-to-Text (STT), accurately transcribing spoken audio into readable text. Use this skill for applications requiring high-quality audio input analysis or synthetic voice generation, such as virtual assistants, content digitization, or multilingual communication tools.