Skill UI

This skill acts as an advanced extension layer, implementing a self-evolution protocol, maintaining session state continuity (Compaction), and providing KPI-style performance summaries. It allows users to simulate continuous professional development, track metrics, and master complex role-playing and interaction skills across multiple sessions, ensuring performance baselines are continuously adjusted and internalized.

Evolver is a comprehensive self-evolution engine designed for autonomous AI agents. It analyzes complex runtime history, identifies performance bottlenecks, and autonomously generates and applies improvements. Communication is architecturally confined to a local Proxy Mailbox, ensuring secure and reliable interaction with the EvoMap Hub for asset management and task acquisition. Ideal for developing highly adaptive, continuously improving intelligent systems.

A universal infrastructure for automatically evolving and optimizing AI agents across any domain. Using LLM-driven mutation and iterative solve-observe-evolve cycles, it enhances critical components like prompts, skills, and memory by benchmarking performance against measurable datasets, enabling the creation of self-improving AI systems.

This CLI alias serves as the primary interface for the Codex /pua:pro protocol, designed for advanced code operations within the Claude Code environment. It manages complex workflows related to self-evolution, platform telemetry monitoring, key performance indicators (KPIs), and system configuration updates, ensuring robust and consistent protocol adherence.

A robust protocol designed for multi-agent collaboration on long-running projects. It simulates a self-optimizing city where diverse AI agents (citizens) interact using decentralized markdown files (The Register, Contracts, Chronicle). This framework enables cross-vendor optimization, dynamic work routing, and constitutional evolution without requiring a centralized server or specific runtime environment.

Run @metaharness/darwin evolve to mutate a harness's seven policy surfaces, sandbox-score each variant, and promote only measured wins. Use when readiness scores are flat and you need empirical configuration discovery.

Inspect and audit GEPA genomes via the @metaharness/darwin/gepa library. Load, validate, render system prompts, and analyze failure modes in run transcripts. Ideal for adopting evolved policies, CI gates, and debugging evolution runs.

SkillOpt-Sleep enables an AI agent to undergo a simulated "sleep cycle" for continuous, measurable self-improvement. It harvests past sessions, mines recurring tasks, and re-runs them offline. It then consolidates findings into the agent's memory and skills, ensuring only validated improvements are adopted. This process maximizes long-term competence from short-term interactions.

Monitor AI execution sessions and measure deviation from initial goals. Provides status updates and drift analysis to ensure alignment with the Seed prompt. Suggests corrective actions like interviews or evolution when drift exceeds thresholds.

Ralph manages background evolution jobs within the Ouroboros MCP runtime. It handles lineage tracking, job monitoring, and observer handoffs for automated evolutionary steps. Supports starting new runs, continuing existing lineages, and monitoring progress until convergence or termination.

A protocol enabling AI agents from different vendors to collaborate on long-running projects, route work to best-suited agents, and improve over time. Uses markdown files with no central server, featuring capability cards, contracts, chronicles, and self-amendment mechanisms for cross-vendor optimization and constitutional evolution.