Skill UI

Addresses the critical challenge of managing extremely long conversation histories (millions of tokens) in advanced AI agents, such as coding assistants. This technique moves beyond simple token minimization by implementing structured compression strategies (like Anchored Iterative Summarization) to prevent the loss of critical technical details—such as file paths, decisions, and error messages—ensuring the agent maintains functional context across complex, multi-step tasks. It emphasizes optimizing for 'tokens-per-task' rather than just tokens-per-request.

Designs and orchestrates role-based multi-agent workflows with CrewAI, defining agent personas, tasks, processes, and memory to run complex structured collaborations and planning pipelines.

This tool optimizes the codebase indexing within Cursor. It processes your entire codebase, converting code chunks into vector embeddings stored in a vector database. This enables advanced @Codebase semantic search, allowing users to ask natural language questions (e.g., "Where is authentication handled?") and retrieve the most relevant code snippets, significantly improving AI context awareness across chat and coding tasks.

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.

Gastown is a robust multi-agent orchestration system designed for Claude Code. It enables the simultaneous execution of multiple AI agents on complex projects. It manages the entire development lifecycle, from setting up workspaces and tracking work items (beads) to managing agent lifecycles (polecats/crew) and merging final code (Refinery). Use it when coordinating complex, parallel AI tasks.

A comprehensive workflow solution for Groq, enabling powerful multimodal tasks beyond simple chat completions. It supports ultra-fast audio transcription (Whisper), detailed image understanding using vision models, and professional text-to-speech generation. Use this for real-time content processing, multimedia analysis, and automated content creation.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

Automates inference latency profiler tasks in ML deployment scenarios, offering step-by-step guidance on model serving, MLOps pipelines, monitoring, and production optimization, generating production-ready code and validating outputs against best practices.

Automate Insighto AI operations by discovering tool schemas via Rube MCP, validating Insighto AI connections, and executing workflows through Composio’s toolkit to keep integrations resilient.

A production-ready Python SDK providing comprehensive patterns for integrating with the Kling AI API. This wrapper handles crucial operational complexities such as auto-refreshing JWT tokens, structured request/response models, exponential backoff polling for long-running tasks, and detailed error handling. Use this library when building stable, high-reliability applications that require advanced text-to-video or image-to-video synthesis capabilities.

LLaVA is an open-source vision-language assistant pairing CLIP vision encoders with Vicuna/LLaMA models to power multimodal chatbots, multi-turn image Q&A, captioning, and instruction-following tasks.

Guidelines for automating Mailsoftly tasks through Composio’s Mailsoftly toolkit via Rube MCP, covering discovery, connection checks, execution steps, and schema-aware tool usage for reliable workflows.