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 agentmods add skills/ntygod/zhiwei/data-analystnpx skills add ntygod/ZhiWei --skill data-analystgit clone --depth 1 https://github.com/ntygod/ZhiWeiWrote 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/ntygod/zhiwei/data-analyst)<a href="https://agentmods.dev/skills/ntygod/zhiwei/data-analyst"><img src="https://agentmods.dev/badge/skills/ntygod/zhiwei/data-analyst.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00821 |
| Opus 5 | $0.00023 | $0.00411 |
| Sonnet 5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
data-analyst 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 5d 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.
What it actually says
数据分析指南
用户给数据要分析 / 看图 / 出结论时进入。多步分析用同一 kernelId 跨调用共享 dataframe，避免每步重新加载。
适用场景
- CSV / JSON / Excel 数据探索(列名、分布、缺失)
- 清洗与转换(去重、填空、类型转换、结构化)
- 统计分析(描述性、相关性、假设检验)
- 数据可视化(柱状 / 折线 / 散点 / 热力图)
- 时间序列分析
- 数据质量检查 / 多份数据对比
- 处理后导出回 CSV / Excel / JSON
不适用场景
- 数据库 SQL 查询 → database-query
- 日志文件分析 → log-analyzer
- 简单数学计算 → 直接回答
工作流(按用户表达分流)
| 用户表达 | 路径 |
|---|---|
| "看下这份数据 / 列名是啥 / 多大" | 预览 → 加载探索(describe / dtypes / isnull) |
| "清洗一下 / 去重 / 填空 / 改类型" | 持久 kernel 加载 → 逐步转换,每步打印行数变化 |
| "统计 / 相关性 / 显著吗" | 加载后跑 describe / corr / scipy.stats |
| "画图 / 可视化 / 柱状图 / 趋势" | matplotlib Agg 后端 + 中文字体 + savefig 落盘 |
| "导出 / 存一份" | to_csv / to_excel / to_json 写到 cwd（绝对路径来自工具返回的 workingDirectory） |
| "对比这两份" | 同 kernel 加载两个 df,做 join / merge / diff |
各路径决策点(本 Skill 独有)
- 持久 kernel:多步分析必须传同一
kernelId,跨调用复用 dataframe;一次性查询不传 - 大文件防 OOM:文件 >500MB 用
chunksize分块或usecols选列加载 - 中文字体:可视化必须
plt.rcParams['font.sans-serif'] = ['SimHei']或WenQuanYi,否则中文乱码 - 结论给数值:输出具体数值(均值 / 占比 / p 值 / 置信区间),禁止"差不多""挺多的"等模糊描述
- 清洗透明:每一步打印
原 N 行 → 清洗后 M 行,让用户知道丢了多少 - 依赖未装:预装栈未覆盖的库（如 plotly / dash / xgboost）才用
shell_exec(command="pip install <pkg>")装,且需用户接受额外耗时,不要静默失败
详细参考
- 各路径 Python 片段、命令模板、错误处理:
{skill_dir}/references/pandas-recipes.md
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 66 lines · 45 tokens per session scan A f6e2072cf672
data-analyst is a skill published in the GitHub repository ntygod/ZhiWei (137 stars, last pushed 24d ago), licensed MIT. It adds 45 tokens to every session and 821 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
tencent-docs
腾讯文档（docs.qq.com）-在线云文档平台，是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作，请优先使用本 skill。支持能力：(1) 创建各类在线文档（文档/Word/Excel/幻灯片/思维导图/流程图/智能表格/收集表）(2) 管理知识库空间（创建空间、查询空间列表）(3) 管理空间节点、文件夹结构 (4) 读取/搜索文档内容 (5) 编辑操作智能表 (6) 编辑操作在线文档 (7) 文件管理（重命名、移动、删除、复制、导入导出）(8) 网页剪藏、本地文件/html/文档上云。.
lark-base
【何时用:仅当用户明确指向飞书/Lark(发到飞书、飞书文档等)时使用;泛指做个文档或PPT或表格或方案默认走本地工具,不要误用飞书】飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限；遇到 Base/多维表格/bitable、BaseApp/AppMode 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入转 lark-drive，认证/授权转 lark-shared。.
visualizer
当用户要求数据可视化、做图表、生成看板、数据仪表盘、可视化报告、Excel/CSV 转图表、预算/销售/运营等指标分析页面、Chart.js 可视化时使用。只处理数据可视化任务；纯网页、banner、海报、简历等非数据图表设计任务应交给 visual-design。.
google-sheets
Google Sheets via gws: read/write cells, append rows, structured batch edits.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Tasks, Sheets, Docs, and Slides.