Claude Skills by YuYY2004

Scan all date columns in Excel and convert datetime values to user-specified text format (yyyymmdd, yyyy-mm-dd, yyyy/mm/dd, yyyy年mm月dd日, or any custom combination). Supports three output positions: insert new column on left, insert new column on right, or replace original column. New column headers can be customized, defaulting to "{original name}(text)". 扫描 Excel 中所有日期列，将 datetime 转为用户指定的文本格式（yyyymmdd、yyyy-mm-dd、yyyy/mm/dd、yyyy年mm月dd日 等任意组合）。支持三种输出位置：左侧插入新列、右侧插入新列、替换原列。新列表头可自定义，未指定时默认"{原列名}(...

Deduplicate Excel data by key column — keep first occurrence, delete subsequent duplicates. First calls excel-find-duplicates for read-only scanning to find duplicate row numbers, then confirms and deletes via XML direct ops (bypassing openpyxl, 10x faster). Format fully preserved (only rows removed, kept rows unchanged). 对 Excel 数据按关键列去重——保留首次出现的行，删除后续重复行。先调用 excel-find-duplicates 只读扫描找重复行号，确认后通过 XML 直接操作删除（绕过 openpyxl，快 10 倍）。格式完整保留（只删行，不改保留行内容）。 Trigger keywords: "deduplicate" "remove dupl...

Safely delete rows or columns in Excel files. Auto-checks formula dependencies before deletion to prevent #REF! errors. Row deletion uses XML direct ops (10x faster), column deletion uses openpyxl. Supports by index, by name, and batch deletion. 在 Excel 文件中安全删除行或列。删除前自动检查公式依赖，防止产生 #REF! 错误。行删除使用 XML 直接操作（快 10 倍），列删除使用 openpyxl。支持按序号、按名称、批量删除。 Trigger keywords: "delete column" "remove column" "delete row" "remove row" "delete empty rows" "delete empty columns" 触发词包括"删除列""去掉第X列""移除列""删除行""去掉第X行...

Filter Excel data rows by condition — keep or delete rows matching criteria. First uses pandas read-only scan to identify target row numbers, then uses XML direct operations to remove unwanted rows (format-preserving). Supports equals, contains, range, date comparison, and other common filters. 按条件筛选 Excel 数据行——保留或删除符合条件的行。先用 pandas 只读扫描确定目标行号，再用 XML 直接操作移除不需要的行（格式无损）。支持等值、包含、范围、日期比较等常见筛选。 Trigger keywords: "filter" "keep only" "extract" "keep rows matching" "delete rows matching" "by conditi...

Read-only scan of Excel files to find duplicate rows by specified column(s), outputting duplicate row number lists. Does not modify the original file. Typically used in conjunction with excel-delete for safe, format-preserving deduplication. 只读扫描 Excel 文件，按指定列查找重复行，输出重复行号列表。不修改原文件。通常配合 excel-delete 使用实现安全的格式无损去重。 Trigger keywords: "find duplicates" "check duplicates" "scan duplicates" "duplicate rows" "what are the duplicates" 触发词包括"查重""找重复""检查重复""重复行""有哪些重复"。

Uniformly adjust Excel file formatting — font, size, bold, italic, color, alignment (horizontal/vertical), column width, row height. Supports per-scope application: entire sheet, specified columns/rows, headers, data area, or condition-matched cells. 统一调整 Excel 文件的格式样式——字体、字号、加粗、斜体、颜色、对齐方式（水平/垂直）、列宽行高。支持按范围应用：整表、指定列/行、表头、数据区、或条件匹配的单元格。 Trigger keywords: "font" "bold" "italic" "center" "align" "column width" "row height" "change style" "format" "beautify" 触发词包括"字体""加粗""斜体""居中""对齐""列宽""行高""改样式"...

Freeze or unfreeze Excel worksheet panes. Supports freeze top row, freeze first column, freeze top row + first column, freeze at specified position. 冻结或取消冻结 Excel 工作表窗格，支持冻结首行、冻结首列、冻结首行+首列、冻结指定位置。 Trigger keywords: "freeze" "freeze header" "lock top row" "freeze first column" "unfreeze" 触发词包括"冻结""固定表头""锁定首行""首列不动""取消冻结""冻住"。

Safely insert rows or columns in Excel files. Supports inserting columns to the left/right of specified columns, or rows above/below specified rows. Custom header naming and fill content supported. 在 Excel 文件中安全插入行或列。支持在指定列的左侧/右侧插入列，或在指定行的上方/下方插入行。可自定义表头命名和填充内容。 Trigger keywords: "insert column" "add column" "insert row" "add row" "new column" 触发词包括"插入列""加一列""新增列""左边加列""右边加列""插入行""加一行""上面加行""下面加行""在第X列/行前/后插入"。

Batch replace column values by mapping table. User provides mapping relationships (spoken in conversation / pasted list / mapping file), and the skill auto-matches and replaces corresponding values in the target column. Values not in the mapping table are preserved as-is. 按映射表批量替换某列的值。用户提供映射关系（对话直说/粘贴列表/映射文件），技能自动匹配并替换目标列中对应的值。映射表中不存在的值保留原样。 Trigger keywords: "mapping replace" "batch replace" "by lookup table" "convert codes" "corresponding replace" 触发词包括"映射替换""批量替换""按对照表""换成代码""对应替换"。

Merge multiple same-structure Excel files into one — validates header consistency then appends rows. Format inherits from the first file. 合并多个同结构的 Excel 文件为一个——验证表头一致后按行追加。格式继承第一个文件。 Trigger keywords: "merge" "combine" "concatenate" "consolidate" "merge multiple files" "append" 触发词包括"合并""拼接""合在一起""汇总""多个文件合并""追加"。

**Default entry point — all Excel file operations should consider this skill first.** ## Auto-trigger Conditions (any one suffices) / 自动触发条件（满足任一即触发） ### Condition 1: User mentioned an Excel file / 条件一：用户提到了 Excel 文件 As long as an Excel file (.xlsx / .xlsm / .csv / .xls / spreadsheet / workbook / worksheet) appears in context, AND the user is describing an operation to perform on it (modify/format/delete/merge/split/sort/dedup/filter/date/insert etc.), trigger this skill first — even if onl...

Use regular expressions to clean Excel column content — extract, delete, or replace matched portions. Supports three modes: extract (capture matched content), remove (delete matched content), replace (substitute matched content). XML fast path for large files (4x faster). 用正则表达式清理 Excel 某列的内容——提取、删除或替换匹配的部分。支持三种模式：extract（提取匹配内容）、remove（删除匹配内容）、replace（替换匹配内容）。大文件走 XML 快速路径（快 4x）。 Trigger keywords: "regex" "clean" "extract" "remove numbers" "keep only" "clean up" 触发词包括"正则""清理""提取""删除xxx部分""去掉...

Safely replace content in Excel — entire columns, rows, or condition-matched cells. Supports replacing with fixed values, Excel formulas, or Python transform functions. 安全替换 Excel 中的内容——整列、整行、或指定条件的单元格。支持替换为固定值、Excel 公式、或 Python 转换函数。 Trigger keywords: "replace column" "overwrite column" "entire column to" "replace row" "batch replace" "conditional replace" "cell replace" "clean" "change all to" 触发词包括"替换列""覆盖列""整列改成""替换行""批量替换""条件替换""单元格替换""清洗""全部改为"。

Excel safe editing five-step method (Backup→Scout→Plan→Execute→Verify). When users need to do structural editing on existing Excel files (insert columns, delete columns, modify data, format conversion, etc.), use this skill to ensure safe operations and avoid data corruption. Suitable for large files (>10MB or >10K rows) and complex spreadsheets with formulas. Other Excel operation skills reference this skill as their base workflow. Excel 安全编辑五步法（备份→勘察→规划→执行→验证）。当用户需要对现有 Excel 文件进行插入列、删除列、修改数...

Pre-operation reconnaissance — read-only scan of Excel files to locate columns relevant to user needs, output a structured scout report for user confirmation. Makes no modifications. When users describe complex Excel operation needs but haven't specified column numbers/names/current values, use this skill first to understand "what's in the file and which columns need to be operated on." 操作前勘察——只读扫描 Excel 文件，定位用户需求涉及的列，输出结构化勘察报告供用户确认。不做任何修改。当用户提出复杂 Excel 操作需求但未明确指定列号/列名/当前值时，先调用此技能搞清楚"文件里有什么、哪...

Sort Excel data by specified column(s). Supports single or multi-column sort, ascending/descending, numeric/date/text sorting. 对 Excel 数据按指定列排序，支持单列或多列排序、升序/降序、数值/日期/文本排序。 Trigger keywords: "sort" "ascending" "descending" "sort by column" "from small to large" "newest first" 触发词包括"排序""升序""降序""按xx列排列""从小到大""从新到旧"。

Split a large table into multiple files by a specified column (one file per unique value). Uses pandas grouping + iterparse streaming fan-out (single XML parse, multi-output), with format fully preserved. Supports limiting split count (Top N + Others). 按指定列将一个大表拆分成多个文件（每个值一个文件）。用 pandas 分组 + iterparse 流式分流（一次解析XML，多路输出），格式完整保留。支持限制拆分数量（Top N + 其他）。 Trigger keywords: "split" "separate" "split by" "split into files" "break apart by" 触发词包括"拆分""拆开""按xx分开""分表""拆成多个文件"。

Read-only scan of Excel files to check data quality — null rate, outliers, format consistency, duplicate values, etc. Outputs a quality issue report without modifying the original file. 只读扫描 Excel 文件，检查数据质量——空值率、异常值、格式一致性、重复值等。输出质量问题报告，不修改原文件。 Trigger keywords: "check data" "validate" "null values" "data quality" "any issues" "scan" "quality report" 触发词包括"检查数据""校验""空值""数据质量""有没有问题""扫描""质量报告"。