NOVA Memory

AI Agent 三层记忆架构系统。用于构建具有长期记忆能力的 AI 助手。 触发条件：(1) 用户询问记忆系统设计或架构 (2) 需要为 AI Agent 构建记忆能力 (3) 提及"记忆系统"、"情景记忆"、"语义记忆"、"NOVA"、"记忆维护"等相关概念

This skill is an instruction-only blueprint for a file-based long-term memory. Before installing or running it: (1) Inspect and vet all file paths it will read/write (notably /root/.openclaw/* and ~/.openclaw/*) because those may contain sensitive data or credentials. (2) Note it asks you to add cron jobs and perform git commits — these create persistent, recurring behavior; only allow them if you trust the author and understand the exact commands. (3) The SKILL.md references running a node script (skills/self-iterator/iterate.js) and Feishu token extraction but does not include those scripts or declare credentials — confirm where those scripts come from and how secrets will be provided. (4) If you want to use it, test in a sandbox or non-production account, back up existing AGENTS.md and workspace files, and require explicit review/approval before applying cron edits or committing changes. Additional information that would raise confidence to high: a provided implementation (code) to review, explicit list of files/commands the skill will run, and a justification for reading any root-level paths or external credentials.

Type: OpenClaw Skill Name: nova-three-level-memory Version: 1.0.1 The skill bundle defines a 'Three-Layer Memory Architecture' that grants the AI agent significant autonomy to self-modify its core identity and behavioral rules based on conversation history. It instructs the agent to perform high-risk operations such as managing systemd services, cron tasks, and executing shell commands (e.g., 'node skills/self-iterator/iterate.js' and 'git commit') for self-maintenance. This architecture is highly susceptible to persistent indirect prompt injection, where malicious user input could be 'distilled' into permanent system constraints or identity changes.