Skill UI

Automates Rosette Text Analytics actions through Composio’s Rube MCP, guiding users to discover current tool schemas, verify connections, and execute workflows with schema-compliant inputs.

Auto-activating assistant that guides AWS Sagemaker endpoint deployment, from best practices to production-ready code, configurations, and validation for inference serving and monitoring workflows.

Automates Scrapegraph AI operations through Composio’s Rube MCP, guiding you to discover tools, check active connections, execute schema-compliant workflows, and manage sessions and pagination safely.

Provides Meta AI’s Segment Anything Model for zero-shot image segmentation via interactive prompts or automatic mask generation, enabling rapid dataset creation and integration in vision pipelines.

Automates Semanticscholar workflows through Composio’s Semanticscholar toolkit via Rube MCP, covering tool discovery, connection verification, session reuse, and schema-compliant multi-tool execution for reliable research automation.

Comprehensive skill covering the full lifecycle of visual AI systems. Expertise includes object detection (YOLO, Faster R-CNN), instance and semantic segmentation (SAM, Mask R-CNN), and video analysis. The workflow guides users through dataset preparation, selecting optimal architectures, training using frameworks like PyTorch, and achieving production readiness via model optimization (ONNX, TensorRT) and deployment on various edge or cloud targets.

Sentence Transformers provides 5000+ pre-trained models that generate sentence, text, and image embeddings for RAG, semantic search, clustering, and multilingual production workloads without relying on external APIs.

Orchestrates Serpapi searches through Composio's Rube MCP by discovering current tool schemas, validating the connection, and executing schema-compliant calls with session reuse and explicit memory placeholders to keep automation workflows reliable.

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

This skill provides comprehensive patterns and best practices for implementing efficient similarity search mechanisms using vector databases. It is essential for building advanced AI systems such as semantic search engines, implementing Retrieval-Augmented Generation (RAG), and developing recommendation systems. Use this when optimizing retrieval performance or scaling to massive volumes of vectors.

SimPO (Simple Preference Optimization) is a state-of-the-art, reference-free method designed for aligning Large Language Models (LLMs) using human preference data. It is an efficient alternative to DPO and PPO, notably outperforming DPO without requiring a separate reference model. It is ideal for practitioners who need faster, simpler, and more resource-efficient fine-tuning for preference alignment.

Documented steps to automate Skyfire operations through Composio’s Rube MCP endpoints, covering tool discovery, connection checks, execution patterns, and schema compliance for reliable workflows.