Skill UI

This utility initializes a brand-new Ruflo project environment. It sets up all necessary underlying components, including MCP tools, hooks, and agent configurations. It is essential for developers starting a project in a fresh repository, allowing selection between standard, minimal, or full presets to bootstrap the entire system.

This system optimizes task execution by recommending the best agent and model tier (Haiku, Sonnet, Opus) based on learned patterns and a 3-tier routing model. It ensures auditable decisions by emitting a detailed routing rationale. Use this before starting any non-trivial task to replace manual selection with data-driven decisions, and record outcomes to continuously improve the router's accuracy.

This pattern is designed to solve context limitations in complex multi-agent workflows. Instead of relying on a single, massive context dump, it implements a structured, multi-cycle loop (Dispatch -> Evaluate -> Refine -> Loop). This process iteratively refines the search query by scoring content relevance and identifying missing context gaps, ensuring sub-agents gather the most targeted and highly relevant information needed for tasks like debugging or feature implementation.

This skill guides the architectural design of an Itô Data Atlas agent for advanced quantitative research. It facilitates market discovery, constructs candidate prediction-market baskets, drafts necessary parameter changes, and integrates human-in-the-loop review. It is strictly for workflow and architectural planning, and does not execute live trading orders.

This robust tool extracts structured entities (classes, functions, modules, types, concepts) and their complex relationships (imports, inheritance, calls) directly from source code files. It builds a comprehensive and weighted knowledge graph stored within AgentDB. Ideal for deep codebase analysis, dependency tracking, and impact assessment in large software projects.

A comprehensive guide for optimizing systems requiring ultra-low latency and high freshness, such as real-time dashboards, market data feeds, streaming agents, and HFT infrastructure. It details how to measure critical metrics (p95 latency, throughput, freshness age) across the entire 'hot path,' providing structured steps for optimization, caching, and rigorous verification to ensure performance reliability.

This skill provides comprehensive security and monitoring for Large Language Model (LLM) powered trading agents. It helps to audit trade decisions, ensure compliance with risk parameters, and mitigate potential risks associated with automated financial operations.

This skill guides the design and rigorous review of goal-oriented feedback loops for autonomous agents. It helps users define machine-decidable exit criteria, select the appropriate loop type (e.g., servo, regulator), and test the workflow against common failure modes like spinning, goal-gaming, or running past the correct answer. Use it when building complex, iterative, or self-correcting agent workflows.

This skill provides access to Anthropic's Claude Managed Agents, offering a robust cloud environment for executing complex, long-running AI workflows. It handles the entire agent lifecycle, from provisioning the container and environment (create), to executing multi-turn prompts, monitoring status, and ensuring proper cleanup (terminate). Ideal for critical, asynchronous tasks that require persistent state and advanced tools.

This memory bridge imports local auto-generated memories from Claude Code into a centralized AgentDB knowledge base. It generates ONNX embeddings, deduplicates entries using cosine similarity, and enables unified semantic search across all projects and sessions. It is essential for building comprehensive, context-aware AI applications.

A comprehensive, end-to-end methodology designed for software engineers and AI agents to safely and systematically integrate machine learning models into existing non-ML codebases. It guides users through critical phases, including problem framing, data readiness, architectural decoupling (via APIs/services), baseline model implementation, and final MLOps pipeline setup.

Use the Monitor tool to achieve real-time observability of swarm events instead of relying on periodic polling. This utility streams comprehensive NDJSON events, including agent spawns, task completions, memory writes, and health checks. It is designed for developers and engineers needing immediate insight into the operational status and health of a distributed system.