Memory

self-improving-agent curates Claude Code auto-memory by reviewing MEMORY.md, promoting proven patterns to CLAUDE.md or .claude/rules/, and extracting reusable skills. Use it for memory health checks, evidence-backed rule promotion, and Context Engineering workflows where project knowledge must become durable.

review audits Claude Code auto-memory in MEMORY.md to find promotion candidates, stale references, duplicates, consolidation opportunities, and health checks for Context Engineering workflows.

remember explicitly saves important facts, decisions, conventions, and gotchas to Claude auto-memory with timestamped context, duplicate checks, and a simple /si:remember workflow.

promote graduates proven Claude auto-memory patterns from MEMORY.md into CLAUDE.md or .claude/rules/ so useful behaviors become durable project rules. Use it with /si:promote to confirm evidence, choose the right target, and write scoped instructions for self-improving Context Engineering workflows.

context-compression is a practical skill for shrinking long agent sessions without losing the facts needed to continue work. It helps with context compression, structured summarization, file tracking, decision preservation, and tokens-per-task optimization for long-running coding tasks and Context Engineering workflows.

mnemos is a task-scoped memory skill for agents that need durable context across compactions. It uses a typed MnemoGraph to keep goals and constraints persistent, compress results, and preserve checkpoints for resume. Useful for context engineering, debugging, repo maintenance, and handoffs.

read-memories is a Claude Code skill for searching prior session logs to recover decisions, patterns, unresolved TODOs, and user corrections. Use it when a task depends on earlier context, across ongoing projects, or for read-memories for Workflow Automation. The read-memories skill helps agents find evidence quickly instead of guessing from memory.

memory-systems is a guide for designing agent memory that persists across sessions. It covers backend-focused architecture choices, including vector stores, entity graphs, and temporal knowledge graphs, plus when to use each. Use this memory-systems skill to plan durable retrieval, entity continuity, and long-term state for agents.

memorize is a Skill Authoring and agent workflow skill that curates reflections, critiques, and execution feedback into durable, actionable guidance in CLAUDE.md using Agentic Context Engineering. Use it when lessons should survive beyond one chat and improve future runs.