自动追踪用户情绪变化，在合适的时机关心用户。检测对话情绪、记忆历史、主动关心、周报生成。

This skill appears coherent and runs locally. Before installing, consider: (1) it stores message snippets and timestamps in ~/.memory/emotions/history.json — that can contain sensitive/PII; inspect or remove that folder if you don't want local records; (2) set filesystem permissions or encrypt the file if privacy is important; (3) the skill does not transmit data externally or require credentials, but review the code if you want to confirm behavior; (4) if you prefer no automatic care messages, call detect_emotion without acting on returned care_message or modify the code to disable auto-care logic. Note: small logic issues (e.g., keyword duplication) affect detection accuracy but are not security issues.

Type: OpenClaw Skill Name: emotion-memory-assistant Version: 1.0.0 The skill is a straightforward emotion tracking assistant that stores user sentiment history locally in the user's home directory (~/.memory/emotions/). The implementation in emotion_memory.py uses basic keyword matching to detect moods and provides supportive response templates without any network activity, external dependencies, or suspicious execution logic.