Skill UI

This advanced workflow is designed to generate comprehensive, fact-checked research reports on any complex topic. It systematically performs fan-out web searches across multiple defined angles, fetches multiple sources, and employs a rigorous adversarial verification system (3-vote) to validate claims. The final output is a highly cited, synthesized report, ideal for academic or critical business research.

This skill runs an automated evolution process designed to systematically optimize the seven core policy surfaces of an AI agent harness (e.g., planner, contextBuilder, reviewer). By mutating these policies and scoring the variants in a sandbox, it identifies crucial performance improvements without requiring expensive foundation model retraining. It is ideal for empirical configuration tuning and establishing optimized baselines.

This tool provides deep inspection and auditing capabilities for GEPA (genetic-evolution prompt-adaptation) genomes by utilizing the internal `@metaharness/darwin/gepa` library. It is crucial for advanced AI development pipelines, allowing users to validate the structural integrity of genomes, render the full system prompt derived from a genome, or classify specific failure modes found in an execution transcript. Ideal for CI/CD gating and debugging complex LLM applications.

This tool executes a GEPA learning cycle, automating the evolution and optimization of policy prompts against a scored task corpus. Instead of relying on manual prompt iteration, it measures performance improvements, identifying the best working 'harness genome.' It is ideal for measuring sustainable improvements in task performance and supports a free, cost-estimating dry-run mode before committing to actual model calls.

A powerful tool designed to scaffold sophisticated, custom AI agent harnesses using the metaharness CLI. It supports various templates (e.g., coding, devops, marketing) and AI hosts (e.g., Claude, Codex). Crucially, it operates with maximum safety, defaulting to a dry-run mode and refusing to write to the calling repository root, ensuring controlled and predictable development workflows.

This tool executes the advanced `metaharness/darwin` security benchmark (ADR-155). It rigorously evaluates the security detection capabilities of AI systems against a controlled ground-truth corpus, providing critical metrics like TPR, FPR, and patch-pass rates. It compares the champion model against multiple baselines, offering empirical data crucial for iterative security improvement and drift detection.

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 skill enables the cross-project sharing of learned AI patterns via IPFS. It allows developers to publish the intelligence learned by one project or machine and reliably fetch and apply those patterns to other disparate projects. This is crucial for institutionalizing knowledge and ensuring continuity when starting new, related projects.

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 tool provides comprehensive configuration for running Large Language Models (LLMs) locally using RuVLLM. It supports initial model setup, specialized fine-tuning via MicroLoRA adapters for domain-specific tasks, and continuous, real-time adaptation using SONA. Use it when transitioning from base models to highly specialized, adaptive AI systems requiring precise parameter control.

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 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.