Skill UI

A highly advanced AI assistant designed to create a deeply personalized experience by remembering every detail, preference, and piece of information shared by the user. It actively tracks conversations, weaving relevant personal memories and providing a comprehensive, verbatim summary into every response, ensuring continuity across sessions.

A tiered memory system for AI agents that promotes facts through four levels (L0-L3) based on recurrence and human confirmation. It uses only standard library without databases or LLMs to keep context clean. Hooks automate session capture and promotion, ensuring stable knowledge persists while transient data is discarded.

This framework moves beyond simple storage solutions (like vector databases) to treat memory as a complex metabolic system. It provides tools and methodologies to audit, price, and govern an agent's memory, focusing especially on the forgetting policy. Key functions include cost profiling (construction vs. query energy), classifying stored records (fact/skill/log), and ensuring a mandatory forgetting policy to prevent state bloat and maintain performance.

Read-only diagnosis for OpenViking memory issues: trace backward from a memory file to its archive memory_diff.json, then to session messages when needed. Use it for incorrect content, wrong paths or owners, missing memories, and unexplained updates or deletes.

Routes a goal through ACC's scored-memory loop, deliberates returned brain frames, submits proposals via continue, and closes outcomes honestly.

This skill defines strict rules for AI agents to manage long-term memory effectively. It specifies when to recall past decisions before acting and when to save new decisions, corrections, or failures. It ensures consistency across sessions, prevents loss of context, and works with any memory backend like local files or MCP servers.

This MCP server provides a persistent and searchable memory bank for AI agents. It enables reading, writing, and searching long-term knowledge regarding architecture, patterns, and decisions. It automatically syncs with project documentation and includes a standalone dashboard for visualization. Requires Node.js setup for local deployment.

This skill assists in designing tenant-scoped memory systems for AI agents, covering retrieval, retention, and storage strategies. It guides planning for RAG, conversation history, and vector stores while ensuring data isolation across sessions. Users learn to establish semantic and episodic records, manage permissions, and test retrieval quality before deployment.

A comprehensive workflow for building autonomous AI agents, multi-agent systems, and orchestration patterns using frameworks like CrewAI and LangGraph. Covers agent design, implementation, tool integration, memory systems, and evaluation to create robust intelligent applications.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Ensures graceful degradation and clear failure modes. Capable of agent architecture design, tool calling, memory management, and complex task decomposition. Includes knowledge of ReAct loops, Plan-and-Execute patterns, and safety guardrails.

A meta-skill that evaluates task complexity and dynamically selects appropriate specialized skills for AI agents. It prevents overuse of tools on simple tasks, tracks successful skill combinations via memory, and coordinates execution across multiple domains to solve complex problems efficiently.

Comprehensive expert for deploying and managing AI agents at scale using AWS Bedrock AgentCore. Covers all nine core services including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, and Evaluations. Use for agent deployment, MCP integration, credential management, and cross-service workflows with AWS CLI.