情感记忆助手

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。

Security Scan

The skill's code and instructions match its description: it analyzes messages for emotion keywords and stores local history (~/.memory/emotions/history.json); it does not request credentials or call external endpoints.

Purpose & Capability

Name/description (emotion tracking, care messages, weekly reports) align with the included Python implementation and SKILL.md. Required binary (python3) is appropriate and no unrelated resources or credentials are requested.

Instruction Scope

SKILL.md examples and runtime instructions are limited to detecting emotion, recalling history, sending care messages, and generating reports. The code only reads/writes the declared local storage path and does not instruct reading unrelated files or environment variables.

Install Mechanism

No install specification; the skill is instruction-only plus a Python file. Nothing is downloaded or installed by the skill itself.

Credentials

No environment variables or external credentials are required. The only persistent artifact is a local JSON file under the user's home directory (~/.memory/emotions/history.json), which is proportional to the stated purpose.

Persistence & Privilege

always is false and the skill does not modify other skills or global agent settings. It persists only its own history file in the user's home directory, which is expected for this functionality.

Assessment

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.

情感记忆助手 (Emotion Memory Assistant)

自动追踪用户情绪变化，在合适的时机关心用户。

功能

• detect_emotion - 检测对话中的情绪关键词
• recall_emotion_history - 查询历史情绪记录
• send_care_message - 发送关心消息给用户
• generate_weekly_report - 生成每周情绪报告

情绪关键词库

正向情绪: 开心、高兴、愉快、兴奋、满意、舒服、快乐、幸福

负向情绪: 难过、伤心、焦虑、担心、害怕、沮丧、低落、郁闷、烦、生气、失望

中性状态: 忙、累、困、无聊

主动关心机制

当检测到用户负面情绪，且距离上次关心超过30分钟，自动发送关心消息。

使用示例

from emotion_memory import detect_emotion, recall_emotion_history, generate_weekly_report

# 检测情绪
result = detect_emotion("今天基金亏了，心情不好...")
print(result)

# 查询历史
history = recall_emotion_history(days=7)

# 生成周报
report = generate_weekly_report()

数据存储

• 历史记录: ~/.memory/emotions/history.json

---

By Miya - 2026