三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。

This skill appears to implement the advertised three-tier memory system, but there are several mismatches between the documentation and the code you should review before installing: (1) The docs ask for a YAML config but the script uses a JSON config file; (2) The docs mention automatic summarization via LLMs, yet the script currently uses a local placeholder summary routine (no LLM network calls) — if you expect integrated LLM summaries you must inspect/modify code to provide the intended API hooks and ensure credentials are handled safely; (3) The script writes files into WORKSPACE_DIR (default /Users/scott/.openclaw/workspace) but the SKILL.md does not declare or highlight this environment variable — set WORKSPACE_DIR to an isolated directory or inspect the default path before running; (4) The long-term store uses chromadb if installed; installing third-party Python packages should be done in a virtualenv and reviewed. Recommendation: review the included scripts/memory_manager.py source yourself (or run it in an isolated environment), confirm where files will be written, and only enable LLM/network integrations after verifying how credentials would be provided and stored. If you need higher assurance, request a version that actually integrates with your intended LLM backend and documents required env vars and install steps.

Type: OpenClaw Skill Name: monica-three-tier-memory Version: 1.0.0 The OpenClaw AgentSkills bundle 'monica-three-tier-memory' is designed to manage an AI agent's memory across short, medium, and long terms. All file operations are confined to the designated `WORKSPACE_DIR` (either from an environment variable or a local default path). The `SKILL.md` and `references/references.md` files provide clear, benign instructions and usage examples, with no evidence of prompt injection attempts. The `scripts/memory_manager.py` script correctly handles local file storage and uses `chromadb` for vector storage within the workspace. The `generate_summary` function is noted as a `TODO` for actual LLM integration, indicating an incomplete feature rather than a security flaw. No indicators of data exfiltration, unauthorized execution, persistence, or obfuscation were found.