“Agent memory”

Readonly audit of agent definition files in agents/ for memory & self-learning patterns, debugging patterns, description alignment, and contradicting…

Validates and bootstraps Amazon Bedrock AgentCore observability so customers can trace agent reasoning, detect silent failures, and measure performance before…

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

Relay cross-agent memory.

Diagnose and fix broken memory search in OpenClaw.

Open the local Memory Atlas Web UI (memory-eternal) from Codex or Claude Code.

Cross-check the agent's own answer with independent reviewers before bringing it to the user.

Use this skill when the user asks about recent AI research on token efficiency, prompt compression, inference cache compression, prompt caching, agent memory…

Turn completed or reviewed work into reusable future-agent memory, follow-up issues, plan updates, and bounded active context.

Install or repair the ai-memory companion for Claude Code, Cursor, Codex and Gemini (native macOS binary, LaunchAgent, MCP + lifecycle hooks) while keeping…

Save insights from completed tasks to role memory.

Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect…

Recall prior role memory when cross-session context materially affects the current task.

Manage the project Knowledge Graph; create associative links between concepts, code, and decisions.

Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session.

Use when saving, recalling, resuming, forgetting, summarizing, or listing Agentmemory project memories and sessions, including commit history and commit…

Run ruflo — an agent meta-harness with 314+ MCP tools, multi-agent swarms, vector memory, federation and 30+ plugins.

Audit Claude Code memory for stale, duplicated, or unsourced facts.

End-of-session adversarial review loop.

The _memory/ directory schema for durable project context.

Eve's 5-layer memory system — context, memos, obsidian, ragflow, notebooklm.

使用 MEMORY.md 索引、主题文件和模块化规则包管理持久化项目内存。

End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff.

Reconcile the project's documents with what the code now shows, after a merge or at the end of a build: spec statuses (building → done only with a named gate…