Life Logging Analyzer

Analyze fragmented life data from calendars, health apps, and notes to identify patterns, trends, and build a personal timeline narrative.

Security Scan

The skill's stated purpose (analyzing personal life logs) lines up with its instructions and it requests no unusual installs or credentials, but the runtime instructions are high-level and leave open how personal data will be accessed—so verify data access methods and provenance before use.

Purpose & Capability

Name and description match the instructions: extract patterns from calendars, notes, photos metadata, health apps, etc. The skill does not request unrelated credentials, binaries, or config paths, which is consistent with an analysis/aggregation tool.

Instruction Scope

SKILL.md gives high-level steps (identify available data sources, normalize time series, run 5‑dimensional analysis, generate reports). It does not specify how the agent should access data (user-provided exports vs. reading local system files or invoking external APIs). That ambiguity gives the agent broad discretion at runtime—acceptable if the agent prompts users to supply exports, but risky if it attempts to access account tokens or system files without explicit consent.

Install Mechanism

Instruction-only skill with no install spec and no code files. This minimizes on-disk risk—nothing is fetched or installed by the skill itself.

Credentials

The skill declares no required environment variables, credentials, or config paths. This is proportionate to the stated purpose as long as the agent asks the user to provide or upload the necessary data rather than requesting account credentials.

Persistence & Privilege

always:false and user-invocable:true (defaults). The skill can be invoked autonomously by the agent per platform defaults, but it does not request persistent presence or modify other skills or system configuration.

Assessment

This skill appears coherent with its purpose and is low-risk as provided (no installs, no credentials). Before using it: 1) Confirm how it will obtain your data—prefer uploading/exporting files (calendar .ics, photo metadata, health export) rather than granting account tokens or filesystem access. 2) Do not share cloud passwords, OAuth tokens, or platform keys; provide only the minimum exports or samples needed. 3) Because the skill's source and homepage are unknown, ask the publisher for a privacy statement or viewable implementation (or use open-source alternatives) before sending sensitive health/location data. 4) If the agent asks to read local files or connect to third-party services, decline until you understand and approve the exact access method. Following these steps will reduce the risk of accidental data leakage.

生活日志分析器 — 从碎片化生活记录中提取模式、洞察和趋势，构建个人时间线叙事。

Description

将散落在日历、笔记、照片元数据、健康App、屏幕时间等数据源中的生活轨迹，结构化为可分析的时间线。通过模式识别发现生活节奏、习惯变化和长期趋势。

Usage

当用户需要：

• 回顾过去一周/月/年的生活模式
• 发现时间分配黑洞
• 建立个人生活数据库
• 生成生活年度报告
• 对比不同时期的生活状态

使用本 Skill。

Key Concepts

1. 五维生活日志模型

• 时间维：日历事件、屏幕时间、应用使用时长
• 物理维：位置轨迹、步数、睡眠、运动
• 数字维：消息频率、社交媒体活跃度、代码提交
• 内容维：笔记关键词、照片标签、阅读书目
• 情绪维：心情记录、能量水平、压力指标

2. 模式提取三阶法

• 微观模式（日级）：注意力峰值时段、触发分心的首因
• 中观模式（周级）：工作-休息节奏、社交-独处比例
• 宏观模式（年级）：兴趣演变轨迹、生活重心迁移

3. 叙事生成引擎

• 原始数据 → 统计摘要 → 因果假设 → 人类验证 → 个人叙事
• 关键原则：数据提出假设，人类确认因果，避免伪相关

Instructions

1. 确定用户可用的数据源
2. 建立统一的时序数据格式
3. 运行五维相关性分析
4. 生成模式报告（日/周/月/年）
5. 提出可执行的优化建议

Examples

输入: "帮我分析上个月的时间都去哪了" 输出: 五维时间分配图 + TOP5时间消耗 + 与上月对比 + 3个优化建议

Boundaries

• 不要求完美的数据覆盖，部分数据也能产出洞察
• 隐私优先：所有数据本地处理
• 不做心理健康诊断

References

• Quantified Self 运动
• 个人知识管理(PKM)实践
• 时间感知心理学