system-data-intelligence-skill
专为需要直接操作系统应用并进行深度数据分析的场景设计。 【强制触发场景】： - 用户提及 Excel、WPS、Word、TXT、Markdown、RTZ 等文件的读取/写入/操控 - 用户想从任何应用中「抓取」「提取」「获取」数据 - 用户需要对数据进行「深度分析」「趋势研究」「异常检测」「预测」 - 用户要求生...
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install system-data-intelligence-skill或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install system-data-intelligence-skill⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/system-data-intelligence-skill/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: system-data-intelligence description: > 专为需要直接操作系统应用并进行深度数据分析的场景设计。
【强制触发场景】： - 用户提及 Excel、WPS、Word、TXT、Markdown、RTZ 等文件的读取/写入/操控 - 用户想从任何应用中「抓取」「提取」「获取」数据 - 用户需要对数据进行「深度分析」「趋势研究」「异常检测」「预测」 - 用户要求生成「图表」「可视化」「仪表盘」「数据报告」 - 用户说「帮我看看这个文件里...」「分析一下这份数据...」「做个图表展示..." - 任何涉及跨应用数据流转的任务
【核心能力】：系统接口调用 × 数据深度分析 × 专业可视化
IMPORTANT: 只要涉及文件操作、数据分析、可视化中的任何一项，必须使用此 skill。 不要因为任务「看起来简单」就跳过——底层接口调用有很多坑，skill 里有避坑指南。 ---
收到任务时，先判断类型：
用户任务
├─ 涉及文件/应用操作？
│ ├─ Windows → 走 [WIN-PATH]
│ ├─ macOS → 走 [MAC-PATH]
│ └─ Linux → 走 [LINUX-PATH]
├─ 纯数据分析（已有数据）？→ 走 [ANALYSIS-PATH]
└─ 数据可视化？→ 走 [VIZ-PATH]遇到组合型任务（最常见）：先读文件 → 再分析 → 最后可视化。
---
# 执行: python scripts/win_excel_reader.py <filepath> [sheet_name]# 执行: python scripts/doc_parser.py <filepath>Quit() 释放 COM 进程"KET.Application"（表格）/ "KWPS.Application"（文字）openpyxl 的 read_only=True 模式> 详细 API 手册 → references/windows-api.md
---
# 执行: python scripts/mac_excel_reader.py <filepath> [sheet_name]> 详细 API 手册 → references/macos-api.md
---
# 执行: python scripts/doc_parser.py <filepath>
# 支持 .xlsx .xls .xlsm .csv （无需 Office）# LibreOffice headless 转换为现代格式
libreoffice --headless --convert-to xlsx input.xls --outdir /tmp/
libreoffice --headless --convert-to docx input.doc --outdir /tmp/sudo apt install fonts-noto-cjk> 详细 API 手册 → references/linux-api.md
---
Level 1: 描述性分析 → 数据现状是什么？（均值、分布、缺失率）
Level 2: 诊断性分析 → 为什么会这样？（相关性、异常根因）
Level 3: 预测性分析 → 未来会怎样？（趋势、预测模型）
Level 4: 规范性分析 → 应该怎么做？（优化建议、决策支持）# 执行完整分析
# python scripts/deep_analyzer.py <csv_or_excel_path> [date_col] [value_col]脚本输出：
outputs/analysis_result.json — 结构化分析报告outputs/summary.md — 文字洞察摘要> 详细分析模式 → references/viz-patterns.md
---
数据关系类型
├─ 时间趋势 → 折线图 / 面积图
├─ 类别比较 → 柱状图 / 条形图 / 雷达图
├─ 部分与整体 → 饼图 / 旭日图 / 树状图
├─ 分布情况 → 箱线图 / 直方图 / 小提琴图
├─ 相关关系 → 散点图 / 热力图
└─ 多维关系 → 平行坐标 / 桑基图# 生成交互式仪表盘
# python scripts/viz_engine.py <analysis_result.json> <output_dir>输出：report.html（交互版）+ charts/*.png（静态版）
> 图表模板与最佳实践 → references/viz-patterns.md
---
不确定文件格式时，使用统一入口：
from scripts.doc_parser import detect_and_load
df = detect_and_load("/path/to/any/file")支持格式：.xlsx .xls .xlsm .et .docx .doc .wps .txt .md .rtz .csv .json
---
每次任务完成必须输出：
输出路径：outputs/report_YYYYMMDD_HHMMSS/
---
> 不要问用户想要什么格式——直接给最好的那个。 > 收到文件就分析，分析完就可视化，可视化完就生成报告。 > 每一步都留下日志，每一步都输出可下载文件。 > 用户说「分析一下」，你就给他一份完整的数据故事。
安装 It is designed for scenarios that require direct operating system application and in-depth data analysis. [Forced trigger scenario]: - User mentions reading/writing/manipulating Excel, WPS, Word, TXT, Markdown, RTZ, etc. - User wants to "grab", "extract", and "get" data from any application - User needs to perform "in-depth analysis", "trend research", "anomaly detection", and "prediction" on the data - User requests to generate "charts", "visualizations", "dashboards", "data reports" - users say, "Help me see in this document..." Analyze this data...", "Make a chart presentation..." - Any task involving cross-application data flow [Core Competencies]: System interface calls × Data in-depth analysis × Professional visualization IMPORTANT: As long as it involves any of the file operations, data analysis, and visualization, this skill must be used. Don't skip tasks just because they "look simple" - there are many pitfalls in the underlying interface calls, and there are pitfall avoidance guides in the skills. 后，可以对 AI 说这些话来触发它
Create a WPS Writer report from this sales data and save it as a .docx file
Formats the data into a professional report with headers, tables, and charts, then saves it as a WPS-compatible .docx file
Read the WPS spreadsheet and summarize the key figures
Opens the WPS Spreadsheet file, identifies the main data columns, and returns a plain-English summary of the key metrics
将技能文件夹放到 ~/.claude/skills/system-data-intelligence-skill/ 目录（个人级，所有项目可用），或 .claude/skills/system-data-intelligence-skill/（项目级）。重启 AI 客户端后，用 /system-data-intelligence-skill 主动调用，或让 AI 根据上下文自动发现并使用。
Generate a 10-slide WPS Presentation from this outline
Creates a structured presentation with title slide, content slides, and a summary, formatted for WPS Presentation
It is designed for scenarios that require direct operating system application and in-depth data analysis. [Forced trigger scenario]: - User mentions reading/writing/manipulating Excel, WPS, Word, TXT, Markdown, RTZ, etc. - User wants to "grab", "extract", and "get" data from any application - User needs to perform "in-depth analysis", "trend research", "anomaly detection", and "prediction" on the data - User requests to generate "charts", "visualizations", "dashboards", "data reports" - users say, "Help me see in this document..." Analyze this data...", "Make a chart presentation..." - Any task involving cross-application data flow [Core Competencies]: System interface calls × Data in-depth analysis × Professional visualization IMPORTANT: As long as it involves any of the file operations, data analysis, and visualization, this skill must be used. Don't skip tasks just because they "look simple" - there are many pitfalls in the underlying interface calls, and there are pitfall avoidance guides in the skills. 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
It is designed for scenarios that require direct operating system application and in-depth data analysis. [Forced trigger scenario]: - User mentions reading/writing/manipulating Excel, WPS, Word, TXT, Markdown, RTZ, etc. - User wants to "grab", "extract", and "get" data from any application - User needs to perform "in-depth analysis", "trend research", "anomaly detection", and "prediction" on the data - User requests to generate "charts", "visualizations", "dashboards", "data reports" - users say, "Help me see in this document..." Analyze this data...", "Make a chart presentation..." - Any task involving cross-application data flow [Core Competencies]: System interface calls × Data in-depth analysis × Professional visualization IMPORTANT: As long as it involves any of the file operations, data analysis, and visualization, this skill must be used. Don't skip tasks just because they "look simple" - there are many pitfalls in the underlying interface calls, and there are pitfall avoidance guides in the skills. 可免费安装使用。请查阅仓库了解许可证信息。
专为需要直接操作系统应用并进行深度数据分析的场景设计。 【强制触发场景】： - 用户提及 Excel、WPS、Word、TXT、Markdown、RTZ 等文件的读取/写入/操控 - 用户想从任何应用中「抓取」「提取」「获取」数据 - 用户需要对数据进行「深度分析」「趋势研究」「异常检测」「预测」 - 用户要求生...
It is designed for scenarios that require direct operating system application and in-depth data analysis. [Forced trigger scenario]: - User mentions reading/writing/manipulating Excel, WPS, Word, TXT, Markdown, RTZ, etc. - User wants to "grab", "extract", and "get" data from any application - User needs to perform "in-depth analysis", "trend research", "anomaly detection", and "prediction" on the data - User requests to generate "charts", "visualizations", "dashboards", "data reports" - users say, "Help me see in this document..." Analyze this data...", "Make a chart presentation..." - Any task involving cross-application data flow [Core Competencies]: System interface calls × Data in-depth analysis × Professional visualization IMPORTANT: As long as it involves any of the file operations, data analysis, and visualization, this skill must be used. Don't skip tasks just because they "look simple" - there are many pitfalls in the underlying interface calls, and there are pitfall avoidance guides in the skills. 属于「Design & Creative」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。