Skill UI

Design a persistent multi-agent operating system on Claude Code with kernel routing, specialist agents, slash commands, file-based memory, and scheduled automation for long-lived projects.

A self-hosted, semantic memory service designed for AI agents. It allows agents to save worklogs, decisions, and notes, and recall this knowledge across sessions based on meaning rather than exact keywords. Using pgvector and structured workspaces, it maintains persistent, context-aware knowledge bases, making it ideal for collaborative AI projects.

This tool accesses a persistent FTS5 knowledge base containing previously indexed project documentation, local content, and session memory. Instead of feeding entire raw sources into the conversation context, it allows users to perform targeted, efficient searches using specific queries and source scoping. This is ideal for quickly retrieving technical details, project specifications, or historical context without lengthy re-reading.

SkillOpt-Sleep provides a mechanism for autonomous agent self-improvement. By simulating a 'sleep' or 'dream' cycle, it harvests past interaction sessions, mines recurring tasks, and replays them through the designated backend. It consolidates learned knowledge into persistent memory and skills, ensuring that only strictly validated improvements are adopted via a held-out gate, simulating long-term competence gain from short-term experience. Ideal for scheduled, background optimization.

This skill provides a comprehensive guide for building scalable Retrieval-Augmented Generation (RAG) pipelines and persistent agent memory using Pinecone as the vector database. It covers index setup, embedding large corpuses, implementing dense and hybrid semantic search, and advanced metadata filtering for real-world production systems. Use this for building searchable knowledge bases and context-aware AI agents.

Atlas Ledger is a critical companion designed to provide lasting 'memory' to project contracts. It automatically processes detected deviations or 'drift' (e.g., from audits or reviews) and distills these instances into formal, actionable contract clauses (WHEN/DON'T/INSTEAD). These clauses are written to a persistent project memory file, Atlas.md. This mechanism ensures that lessons learned from failure are systematically captured, allowing future contract cycles to incorporate these rules, thereby strengthening overall project governance and reliability.

This skill provides a hybrid, persistent, and searchable knowledge memory system specifically designed for enhancing AI agents' capabilities. It allows developers to record, retrieve, and search key knowledge, architectural decisions, and operational memories automatically. Use it to build agents with long-term context and reliable knowledge management, ensuring findings are synced back into project documentation.

Design a persistent multi-agent operating system on Claude Code with kernel routing, specialist agents, slash commands, file-based memory, and scheduled automation for long-lived projects.

Transforms Claude Code into a fully autonomous agent with persistent memory, scheduled operations, computer use, and task queueing. Replaces standalone agent frameworks using native crons, dispatch, MCP tools, and memory. Ideal for continuous automation and self-directed agent loops.

This tool serves as a persistent memory and state manager for complex coding projects within the Claude environment. It allows users to initialize new projects with structured metadata, track detailed session progress (including summaries, decisions, and next steps), and save the entire context reliably. By ensuring project continuity across disconnected sessions, it drastically improves the flow and consistency of the development workflow.

Schedule persistent in-session background workers using CronCreate with five-field cron expressions. Run security audits, optimization, memory consolidation, and codebase mapping on fixed clocks, with optional OS schedulers for jobs that outlive the session.

This framework manages the ingestion, organization, synchronization, and search of knowledge across multiple storage layers, including local files, persistent memory, vector stores, and Git repositories. It provides a structured approach for ensuring knowledge durability, deduplication, and maintaining a 'single source of truth' across complex development and operational contexts.