Skill UI

A persistent memory kit designed for Claude AI agents. It maintains deep context across multiple sessions and projects using a two-layer architecture (hot cache and knowledge wiki). Features include safety hooks, multi-project context isolation, and a /close-day command for daily synthesis, ensuring agents remember complex information and continuously learn.

Query and manage AgentDB through the controller bridge, including semantic routing, hierarchical recall, causal graphs, context synthesis, and pattern store/search across agent sessions.

A mechanism for spawning hierarchical, nested sub-agents up to five levels deep, designed specifically for deep task delegation while managing context limitations. Instead of parallel execution, this ensures that each layer of decomposition receives a fresh context window, preventing the parent agent's context budget from being overwhelmed by complex, multi-step workflows. Ideal for research, verification, and synthesis processes.

A comprehensive guide for conducting rigorous academic literature reviews. It teaches authors how to critically appraise and synthesize conflicting empirical evidence by weighing findings based on credibility, study design, and contextual differences. The framework ensures balance, maintains objectivity, and elevates the quality of academic scholarship.

Coordinates multiple specialized agents via Claude Code's native Agent Tool for complex tasks requiring diverse expertise, such as comprehensive code analysis, feature reviews, and security audits. Enables sequential chains, context passing, and resumable work, with a synthesis protocol for unified recommendations.