Loading...
Loading...
Found 11 Skills
How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.
Event sourcing and CQRS expert for AI memory systemsUse when "event sourcing, event store, cqrs, nats jetstream, kafka events, event projection, replay events, event schema, event-sourcing, cqrs, nats, kafka, projections, event-driven, memory-architecture, ml-memory" mentioned.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
Design short-term, long-term, and graph-based memory architectures
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.
Build applications with the Letta API — a model-agnostic, stateful API for building persistent agents with memory and long-term learning. Covers SDK patterns for Python and TypeScript. Includes 24 working code examples.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version focused on core proactive capabilities.
Diagnose context stuffing vs. context engineering. Assess practices, define boundaries, and advise on memory architecture, retrieval, and the Research→Plan→Reset→Implement cycle.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.