Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rexchengm/fios-skills --skill notion-life-insightsgit clone --depth 1 https://github.com/rexchengm/fios-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rexchengm/fios-skills/notion-life-insights)<a href="https://agentmods.dev/skills/rexchengm/fios-skills/notion-life-insights"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-insights/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rexchengm/fios-skills/notion-life-insights"><img src="https://agentmods.dev/badge/skills/rexchengm/fios-skills/notion-life-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00246 | $0.04001 |
| Opus 5 | $0.00123 | $0.02001 |
| Sonnet 5 | $0.00049 | $0.00800 |
| Haiku 4.5 | $0.00025 | $0.00400 |
Grade A, and why
notion-life-insights scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion 生活洞察（Life Insights）
概述
跨库分析与诊断。用户的 Notion 已经按维度聚合成 9 个 监管 数据库（时间 / 知识 / 人际 / 习惯 / 财务 / 旅游 / 家庭 / 影视 / 复盘）和带 元气值 + 对照组 列的 第二大脑 看板。本 skill 把它们串起来，套用选定的对比方式（对照组基准 / 跟上一周期 / 绝对值），把数字解读成中文叙述，并提出具体行动。
输出留在对话里。 本 skill 不写入 Notion。如果用户想对某条建议采取行动，交接给 notion-life-cascade。
REQUIRED BACKGROUND（必备前置）： notion-life-system —— 提供 ntn CLI、scripts/notion_query.zsh、scripts/notion_page_io.zsh、references/notion-intake-rules.json，以及 references/notion-system-schema.md 里的关联/rollup 关系图。
何时使用
当用户想要 分析 / 诊断 / 对比 时使用：
- 看监管数据 / 看第二大脑 / 元气值如何
- 对比上周 / 对比上月 / 跟基准比怎样 / 跟对照比
- 时间花哪了 / 财务情况如何 / 习惯坚持得怎样
- 我哪里做得不好 / 哪里做得好 / 哪里需要调整
- 数据告诉我什么 / 跨维度分析 / 整体趋势
- "分析一下 / 看看" + 一个时间段或维度
不要用于：
- "今日复盘 / 周报 / 月报 / 写日记 / 反思一下" → notion-life-reflection（那些把叙述写进复盘页面）
- "设目标 / 拆任务 / 加打卡" → notion-life-cascade
- 单条记录查询 → 直接用 notion-life-system +
notion_query.zsh
核心循环 —— 5 步
-
Scope（界定范围） —— 确认三件事，只问用户没说的：
- 时间窗: 今天 / 本周 / 上周 / 本月 / 上月 / 季度 / 全年 / 自定义区间。
- 维度: 执行 / 学习 / 财务 / 习惯 / 健康 / 人际 / 旅游 / 影视 / 内容 / 复盘 / 全部。
- 对比模式: 对照组（单周期时默认）/ 跟上一周期（本周 vs 上周, 本月 vs 上月）/ 绝对值（不对比）。
- 只有当多项都不清楚时才用一次 AskUserQuestion；否则直接推进。
-
Read（读取） —— 拉聚合数据，不是原始事件。引用下表里实际的 db 名。
- 单维度:
scripts/notion_query.zsh <监管 db>（一行 = 一条监管维度对象, 内含 rollup 累计）。 - 总览:
scripts/notion_query.zsh 第二大脑—— 当前 vs 对照、元气值、距离最近复盘天数。 - 周期:
scripts/notion_page_io.zsh get <每周/每月复盘 page_id>读公式报告（周报显示, 综合复盘报告, 稳定性分析, 等）。 - 下钻（仅针对某个具体异常）:
notion_query.zsh <底层 db>（如 任务执行, 支出事项, 学习笔记）。 - 除非要下钻，否则绝不拉原始事件表。监管 + 第二大脑 + 复盘 已经有 80% 的答案。
- 单维度:
-
Compare（对比） —— 套用选定的模式。
- 对照组 —— 把每个指标跟它在 第二大脑 里的
*对照列做差。表述为"当前 X vs 对照 Y, 差 Z (+/−%)"。对照列是用户手动维护的基准，不是自动算的。 - 跟上一周期 —— 定位本周期和上周期的 每周/每月复盘 页面 → 对它们的 rollup 做差（任务, 收入, 支出, 专注时长, 学习笔记, 资源, 影视, 事项处理, 健康记录, 书籍笔记）。
- 绝对值 —— 报告当前数字并加少量上下文（分钟→小时, 元→占月度比例 if possible）。不做差。
- 对照组 —— 把每个指标跟它在 第二大脑 里的
-
Insight（洞察） —— 纯中文叙述。有结构但不官僚。
- 关键观察（1–3 条）: 最大偏差、出人意料的稳定、变动最大的维度。
- 异常或趋势（0–2 条）: 值得盯的东西 —— 习惯 7 天掉了 4 天、某类支出飙升、学习时长降 40%。
- 行动建议（1–3 条）: 具体、贴合 schema。"为'写小红书'设个次数打卡每周 3 次" 胜过 "保持创作"。
- 永远引用数字。永远解读它们。绝不说"做得不错"；换成"X 比对照高 Y%"。不要 emoji 刷屏。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 142 lines · 246 tokens per session scan A bf1f9ea3621c
notion-life-insights is a skill published in the GitHub repository rexchengm/fios-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 246 tokens to every session and 4,001 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
spec-to-implementation
Parse specifications and create implementation plans with task tracking in Notion.
meeting-intelligence
Prepare for meetings by gathering context and creating comprehensive agendas.
research-documentation
Research topics and document findings in Notion with organized structure and sources.
knowledge-capture
Transform conversations and discussions into structured Notion documentation.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…