“Agent memory”

Interactive walkthrough of the Memory Kit system using the user's actual project files.

Create and operate a project-scoped research wiki that turns a human seed into an evidence-grounded writing guideline or software implementation plan.

Periodic maintenance of role memory: dedup, tidy, consolidate, and pending management.

Show Engram memory counts, project and topic distribution, recent activity, active tasks, and stored episodes.

Expert in designing and building autonomous AI agents.

Use when designing or reviewing multi-agent systems, subagent orchestration, parallel vs sequential agent execution, context passing between agents, tool…

Cross-platform process memory, dump, runtime, heap, pointer-chain, signature, structure, and memory-forensics analysis for Windows, Linux, Android, Unity…

Forces a memory_search before the agent sends a message containing a factual assertion that has not yet been grounded this turn.

Use when the operator wants durable MCP memories remembered, recalled, explored, consolidated, promoted, or reverted.

Two-tier memory system that makes Codex CLI a true household collaborator.

Merges mature lessons from a domain memory file into its instruction file.

Cross-bot memory on a shared computer (Grok Bot, Cursor plugin, any host where several agents share one machine).

Update memory bank files to keep them accurate for the active development.

This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the…

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates.

Detect persistent instruction injection or long-term memory poisoning.

Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project…

Use when the user wants to review, clean up, or prune the current project's auto-memory files — checking for stale, contradicted, or superseded entries.

Use persistent memory intentionally to retain stable preferences, recurring constraints, and long-lived project context across Codex sessions.

Semantic long-term memory via Mem0 for WhatsApp contacts.

Long-term memory operations for Ferry.

Cross-group memory, search, and event sharing for OpenClaw Feishu agents

Memory and continuity: the RSI tree in `_memory/memora.db` — walk champions and pruned dead-ends before acting, branch and verdict nodes with provenance and…

Record important information to long-term memory for learning user preferences, successful patterns, and error lessons.