多源数据清洗器：把多格式脏表交给 Agent 做解析、去重与合并
多源数据清洗器是 SkillHub 社区数据分析类 Skill（@user_26bdbd50/multi-source-data-cleaner，v1.0.2），通过 Python 脚本完成 Excel/CSV/JSON 等解析、字段识别、去重填充、格式统一，Pro 档支持多源合并、AI 打标与飞书输出。文章说明安装命令、环境变量 DATA_CLEANER_API_KEY 与档位限制，并给出 CLI 与 run_clean_pipeline 示例，便于在 Cursor 等客户端启用。
Read More电商数据清洗skill正式版：面向电商数据分析的 SkillHub 社区技能
电商数据清洗skill正式版（@user_cf88f39e/hbxh-ct）是 SkillHub 上社区发布的 data-analysis 类技能，版本 v2.0.9，标签 requires_api_key=false。公开简介以版本说明为主，未列出详细清洗规则。本文依据 SkillHub 页面与官方安装文档，说明定位、平台数据、通过 skillhub CLI 安装到 Cursor 等客户端 skills 目录的步骤，以及文档粒度与安装可用性等注意事项，并给出官方页面与坐标。
Read More清洗数据：面向内部分析流水线的 SkillHub 数据清洗技能
SkillHub 社区技能「清洗数据」（@user_5f8aef2c/cleandata01，v1.0.0）面向企业内部数据分析：接收原始业务数据，过滤空值、剔除重复并输出标准化数据集，供后续分析技能调用；强调仅处理授权数据、内网闭环。本文基于官方简介与 SkillHub 安装文档，说明定位、核心能力、skillhub CLI 安装路径（Cursor、Claude Code、Codex 等）及对话式典型用法，并提示合规与社区维护注意事项。
Read More数据清洗与分析：在 Agent 里处理表格型数据的 Skill
介绍 SkillHub 社区 Skill「数据清洗与分析」（@user_d9bb652a/data-cleaning-analysis，v1.0.0）。适用于 CSV、Excel、JSON、SQL 等表格数据的缺失值、异常值、重复、类型转换、统计摘要、可视化与相关性分析。说明社区来源、requires_api_key=false，以及通过官方提示词或 skillhub install 安装到 Cursor 等 Agent skills 目录的方法与使用触发方式。
Read MoreExcel数据清洗大师：在 AI 对话里完成 Excel 脏数据预处理
Excel数据清洗大师是 SkillHub 社区 Skill（@user_e9988879/excel-data-cleaner，v1.0.0），面向分析师、财务与运营，覆盖去重、缺失值、格式标准化、异常值检测、分列合并与多表汇总。本文基于官方页面与安装文档说明定位、能力与安装：可用 skillhub install 配合 --dir 装入 Cursor、Claude Code 等 skills 目录，或将官方提示词交给 AI 按 skillhub.md 安装；无需 API Key。典型用法为安装后在对话中描述表格与规则，由 Agent 按 SKILL.md 执行清洗。
Read Moredsh-unique: A Pure Node.js Array Deduplication Plugin
`dsh-unique` is a DeepSeek Harness workflow plugin maintained by uckkk, focused on providing efficient array deduplication. As a pure Node.js implementation, it does not rely on network requests, runs quickly, and is suitable for processing list data locally. After installation, its tool can be invoked directly within a session. The plugin depends on a specific version of the DeepSeek library, and because it involves code execution, it is recommended to review the source code and license before installing.
Read MoreIntroduction to the DSH Plugin: satan9394/dsh-dataset-curation Dataset Curation
`satan9394/dsh-dataset-curation` is a DSH plugin integrated into the DeepSeek Harness workflow, designed to address the cumbersome task of dataset curation in agent development. It supports core functions such as data cleaning, quality filtering, diversity processing, splitting, and annotation. Developers can obtain installation instructions from GitHub; when using the plugin, it should be run with the current process permissions, and users are responsible for reviewing the source code license themselves. This tool is suitable for developers who frequently need to normalize and process datasets.
Read MorePandas Tutorial for Beginners: Missing Value Handling from Entry to Practice
This article introduces methods for handling missing values in data analysis. Missing values refer to non-valid values in a dataset, represented as `NaN` in pandas. Before processing, it is necessary to first check: `isnull()` to mark missing values, `isnull().sum()` to count the number of missing values in each column, and `info()` to view the overall distribution of missing values. Processing strategies are divided into deletion and imputation: Deletion uses `dropna()`, which deletes records containing missing values by row (default) or by column; Imputation uses `fillna()`, including fixed values (e.g., 0), statistical measures (mean/median for numerical values, mode for categorical values), and forward/backward filling (`ffill/bfill`, suitable for time series). Taking e-commerce order data as an example, the case first checks for missing values, then uses the mean to impute the "amount" column and the mode to impute the "payment method" column. The core steps of processing are: check for missing values → select a strategy (delete for extremely few values, impute for many values or key data) → verify the result. It is necessary to flexibly choose methods based on the characteristics of the data.
Read More