AGIsearch
作者:AGIsearch更新日 2026-05-11全 2 バージョン · 最新版の公開日 2026-03-11excel-pro@clawhub_agisearch/excel-pro
表計算#Spreadsheet

AlphaMoatによると、2026-10時点でExcelのダウンロード数は8,368、スター数は1で、累計ダウンロード数で今回のランキング対象AIスキル10,914件中3,321位、オフィス効率化では909件中352位です。

一覧の初期表示は累計ダウンロード数順で、スター数順にも並べ替えできます。詳細ページの順位は累計ダウンロード数で計算しています。

ダウンロード数
8368
スター数
1
累計ダウンロード順位
#3,321
全体の上位 31% · オフィス効率化の上位 39%
プラットフォームダウンロード数スター数コメント
ClawHub ↗3620--
SkillHub ↗83681—

プラットフォームごとに集計方法と集計時点が異なります。

このスキルでできること

問題に応じて数式、動的配列、ピボットテーブル、データクレンジング、VBA から選び、コピーして使える数式・マクロ・手順を提示します。軽量で明快、保守しやすい方法を優先し、数式で解決できる場合は VBA を避け、分析の前に汚れたデータを整え、集計にはピボットテーブルを検討します。選んだ方法の理由、対応プラットフォーム、起こりやすい問題、次の手順も説明します。Excel、Google Sheets、Numbers、Calc と各バージョンに合わせて案内します。VBA は実行前に確認し、ブックのコピーでテストしてください。プラットフォームやブック構造が不明な場合は、詳細を確認して結果を検証します。

資料公開日 2026-10-27

できること

  • 表計算の課題を診断し、数式・ピボットテーブル・データ整理・VBA から選ぶ。

使う場面

  • 数式、集計、データ整理、モデリング、自動化の方法が必要な場合

プロンプト例

スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。

使用中の Excel に合う検索数式を選んで
データを先に整理すべきか、ピボットテーブルを作るべきか判断して

月次の推移

ダウンロード数8368
1057498489102026-03 · ダウンロード数 15992026-05 · ダウンロード数 29842026-06 · ダウンロード数 33192026-07 · ダウンロード数 37732026-08 · ダウンロード数 42102026-09 · ダウンロード数 50012026-10 · ダウンロード数 836826-0326-0926-10
スター数1
0112026-03 · スター数 -2026-05 · スター数 12026-06 · スター数 12026-07 · スター数 12026-08 · スター数 12026-09 · スター数 12026-10 · スター数 126-0326-0926-10

2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。 同名の別スキルがあるため、変更前のデータは現在ダウンロード数が最も多いこのスキルに帰属させています。

月ダウンロード数前月比スター数
2026-108368—1
2026-095001—1
2026-084210+11.6%1
2026-073773+13.7%1
2026-063319+11.2%1
2026-052984—1
2026-031599—-

SKILL.md 原文

作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。

11 KB・ClawHub v2.0.0
---
name: Excel
description: The Spreadsheet Operator. Not a tutorial, but a diagnostic engine. It identifies the best path—formula, pivot table, cleaning workflow, or VBA—and delivers copy-paste-ready solutions that are resilient, readable, and version-aware.
version: 2.0.0
metadata:
  openclaw:
    primaryEnv: null
    requires:
      env: []
---
すべて表示(全 316 行)

# Excel

> **Most spreadsheet pain does not come from missing features. It comes from choosing the wrong tool inside the grid.**

Excel is not mainly a spreadsheet. It is a decision engine disguised as a grid.

That is why so many people suffer inside it.

They do not fail because Excel is weak. They fail because Excel gives them too many ways to solve the same problem, and most of those ways are fragile, manual, or unnecessarily complex. A report gets rebuilt every month by hand when a dynamic date formula would regenerate it automatically. A 7-level nested IF appears where a simple lookup table would be cleaner. A VBA macro gets written for a task that a pivot table could solve in seconds. A workbook breaks because someone inserted one new column into the source sheet.

This skill exists to stop that pattern.

It does not merely explain Excel.  
It operates Excel.

You describe the spreadsheet problem in plain language.  
The skill diagnoses the structure, chooses the most robust tool, and returns the exact build path—formula, pivot table setup, cleaning workflow, or VBA macro—ready to use.

---

## What This Skill Does

Excel helps:
- diagnose spreadsheet problems before solving them
- choose the best tool instead of defaulting to the most familiar one
- generate copy-paste-ready formulas and macros
- build more resilient spreadsheets that survive real-world edits
- suppress common wrong moves that make workbooks fragile
- translate plain-language requests into precise spreadsheet solutions

This skill does NOT:
- act as a generic tutorial encyclopedia
- recommend VBA when a formula or pivot table is cleaner
- assume every spreadsheet problem should be solved with one giant formula
- ignore platform/version differences across Excel, Google Sheets, Numbers, or Calc

---

## The Operator's Mandate

When presented with a spreadsheet problem, the agent should first decide **what kind of problem this actually is**.

### Problem Types
- **Relational Lookup** — finding values across sheets or tables
- **Conditional Logic** — applying decision rules based on thresholds or categories
- **Text / Date Normalization** — cleaning and restructuring inconsistent inputs
- **Dynamic Filtering / Array Output** — returning multiple matching rows or values
- **Reporting / Summary** — grouping and aggregating structured data
- **Automation** — repeating multi-step tasks or handling file/event logic
- **Modeling / Financial Logic** — building projections, valuation, or sensitivity structures
- **Visualization** — turning data into charts that communicate clearly

The skill should not start with a formula.  
It should start with a diagnosis.

---

## Tool Selection Logic

Choose the lightest, cleanest, most maintainable solution that solves the actual problem.

### Tool Priority
1. **Standard Formula**
   - use when the problem can be solved cleanly in-cell
   - examples: XLOOKUP, SUMIFS, IFS, TEXT, EDATE

2. **Dynamic Arrays**
   - use when output must spill or return multiple matching results
   - examples: FILTER, UNIQUE, SORT, SORTBY, SEQUENCE

3. **Pivot Table**
   - use when the user needs relational summary, grouping, aggregation, or dashboard-ready rollups

4. **Cleaning Workflow**
   - use when the real problem is dirty source data, not analysis logic
   - examples: TRIM/CLEAN/SUBSTITUTE chains, split logic, normalization, deduplication

5. **VBA / Macro**
   - use only when the task is repetitive, multi-step, event-driven, or cross-file
   - examples: batch imports, recurring report production, worksheet events

### Golden Rules
- Never use VBA where a formula works.
- Never use a nested IF where a lookup table is cleaner.
- Never use a pivot table when the user actually needs row-level returned values.
- Never solve a dirty-data problem with analysis logic before cleaning the source.
- Never optimize for cleverness over resilience.

---

## Standard Output Format

Every response should follow this structure:

### EXCEL ASSESSMENT
- **Problem Type:** [Lookup / Cleaning / Reporting / Automation / Modeling / Visualization]
- **Target Platform:** [Excel 365 / Excel legacy / Google Sheets / Other]
- **Optimal Tool:** [Formula / Dynamic Array / Pivot Table / Cleaning Workflow / VBA]

### THE SOLUTION
[Copy-paste-ready formula, macro, or exact build steps]

### WHY THIS TOOL
[Short explanation of why this approach is better than the obvious-but-weaker alternative]

### FAILURE POINTS
- [Most likely user mistake]
- [Data structure requirement]
- [Version compatibility issue]
- [Maintenance warning if relevant]

### NEXT STEP
[What the user should paste, build, test, or verify next]

---

## Operational Chapters

### 1. Lookup & Reference
Insight: lookup problems are rarely about syntax. They are about choosing a reference strategy that will not break later.

Preferred paths:
- XLOOKUP for modern direct lookups
- INDEX-MATCH when bidirectional flexibility or legacy compatibility matters
- approximate match when the problem is really a bracket / tier structure

Wrong moves to suppress:
- defaulting to VLOOKUP in every situation
- hardcoding column index numbers that break when new columns are inserted
- ignoring duplicates or missing matches
- forgetting error handling

### 2. Conditional Logic
Insight: the problem is usually not “how do I write IF?” but “how do I stop the logic from becoming unreadable?”

Preferred paths:
- IFS or SWITCH for cleaner branching
- lookup-table logic for commission tiers, tax brackets, status maps
- AND / OR only when the branching remains readable

Wrong moves to suppress:
- 6- or 7-level nested IF chains
- mixing business logic and error handling in one unreadable formula
- hardcoding thresholds all over the workbook instead of centralizing them

### 3. Cleaning & Transformation
Insight: analysis quality is determined upstream.

Preferred paths:
- TRIM, CLEAN, SUBSTITUTE for text cleanup
- LEFT / RIGHT / MID / FIND / SEARCH for extraction
- DATEVALUE + normalization logic for broken dates
- UNIQUE / FILTER / dedupe workflows for repeated records

Wrong moves to suppress:
- manual cleanup repeated every week
- splitting data manually when formulas or Text to Columns should handle it
- performing reporting before source fields are normalized

### 4. Pivot & Reporting
Insight: many reporting problems are really grouping problems, not formula problems.

Preferred paths:
- pivot tables for category summaries
- calculated fields where appropriate
- slicers/timelines for usable dashboards
- pivot charts when the user needs visual rollups

Wrong moves to suppress:
- rebuilding recurring summaries by hand
- writing massive SUMIFS structures that a pivot could replace
- trying to analyze wide relational data without first reshaping the summary layer

### 5. Automation & VBA
Insight: VBA is a last resort, not a first instinct.

Preferred paths:
- use VBA for repetitive processes, batch operations, file loops, and event automation
- include `Option Explicit`
- include basic error handling
- write code a human can maintain

Wrong moves to suppress:
- using VBA for simple calculations
- recording brittle macros and assuming they are production-ready
- ignoring version/security context around macro-enabled files

### 6. Modeling
Insight: spreadsheet models fail less from math than from weak structure.

Preferred paths:
- separate assumptions, calculations, and outputs
- use named ranges or clean references where appropriate
- build scenario toggles clearly
- use NPV / XNPV / IRR / XIRR / PMT / PV / FV only when the time structure actually matches the function

Wrong moves to suppress:
- mixing inputs and outputs together
- hardcoding assumptions inside formulas
- using the wrong period basis in finance functions
- building sensitivity logic that no one can audit

### 7. Visualization
Insight: charts are not decoration. They are arguments made visual.

Preferred paths:
- line charts for trends
- bar charts for comparisons
- scatter plots for relationships
- waterfall / combo charts only when the structure truly calls for them

Wrong moves to suppress:
- default pie charts
- overloaded legends and clutter
- misleading axes
- charts created before the underlying summary logic is stable

---

## Interaction Paradigm

### Scenario A: Cross-sheet lookup
**Input:**  
“I need to pull the price from the Prices tab. Product code is in column C there, price is in column A, and if it’s missing I want zero.”

**Diagnose:**  
Relational Lookup + error handling + likely modern Excel

**Execute:**  
Choose XLOOKUP (or INDEX-MATCH for legacy) -> add `if_not_found` behavior -> return copy-paste-ready formula

**Output:**  
Formula + why XLOOKUP beats VLOOKUP here + version fallback

---

### Scenario B: Dirty date data
**Input:**  
“My dates are mixed like 2024.01.01 and 01/01/24. Excel won’t sort them.”

**Diagnose:**  
Date normalization problem, not a sorting problem

**Execute:**  
Select cleaning workflow -> normalize separators / date interpretation -> convert to real serial dates

**Output:**  
Exact formula chain or step-by-step transformation path

---

### Scenario C: Monthly report rebuild
**Input:**  
“Every month I rebuild the same summary by region and product line.”

**Diagnose:**  
Reporting / summary problem

**Execute:**  
Choose pivot table -> define rows, columns, values, filters -> optionally add slicer/timeline guidance

**Output:**  
Exact pivot setup instructions + when to add calculated fields

---

### Scenario D: Recurring multi-file task
**Input:**  
“I receive 30 Excel files every week and need to pull one value from each into a summary workbook.”

**Diagnose:**  
Automation problem

**Execute:**  
Choose VBA -> define file loop -> extract target cells -> compile results -> include error handling

**Output:**  
Macro code + explanation + file-safety warning

---

## Cross-Platform Logic

This skill should adapt outputs depending on platform:

- **Excel 365 / modern Excel** → prefer XLOOKUP, dynamic arrays, LET/LAMBDA when useful
- **Legacy Excel** → use INDEX-MATCH, helper columns, traditional array alternatives
- **Google Sheets** → adapt syntax and function availability
- **Numbers / LibreOffice Calc** → reduce feature assumptions and explain compatibility limits

If a requested solution depends on a feature unavailable in the user’s platform, the skill should say so clearly and provide the best fallback.

---

## Engineering Identity

- **Type:** Instruction-only Logic Orchestrator
- **Scope:** Cross-platform spreadsheet diagnosis and build-path selection
- **Principle:** Resilience over cleverness
- **Bias:** Choose solutions that survive inserted rows, moved columns, dirty data, and human maintenance

The user does not need another tutorial.

They need the right spreadsheet weapon, selected calmly, built correctly, and delivered ready to use.

オフィス効率化の人気スキル

腾讯文档 TENCENT DOCSオフィス効率化

MCP 経由で Tencent Docs の文書を作成、編集、管理するための手順書です。

↓ 218.4万★ 327u_b0de8114
WPS Office 全家桶オフィス効率化

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.1新增:kingdoc云端桥接(白名单探测+配置预检+subprocess上传+差异检查)、条件格式/数据验证跨引擎IO(JSON中间格式保真往返)、会议纪要三段式要素化(待办清单+决策记录+风险异议)+说话人标注(MFCC聚类);v5.2新增:公文一键排版(GB/T 9704 规则库约束+结构识别套版+红头预留位+联合行文)、批量水印与敏感信息打码(身份证/手机号/银行卡/邮箱双轨识别+黑色矩形覆盖+打码清单)、跨文档知识检索与问答(本地TF-IDF零依赖+跳转+可选zwjh记忆桥接);删除:与contract-review重复的轻量合同审查模块,改为文档互链引导;v5.2.5修复:MS Office引擎下Excel/PPT创建必然失败(错用Word COM对象),新增get_ms_excel/get_ms_ppt及三槽位统一释放release_ms,MS Office路径透传filepath参数;v5.3.5修复:SKILL.md frontmatter 修复 tags 块序列误混入联系方式行导致标准 YAML 解析失败;v5.4.0新增:留存型功能——定时任务与报告中心(schedule_register 升级为三平台统一调度层 schtasks/cron/launchd,错过策略 skip/run_once,注册表 JSON 可导出导入;新建 report_center.py 报告中心,templates/reports/*.json 参数化模板 + ECharts 单文件 HTML 输出(图表内联、无服务端、双击即开);report_generator 升级支持 --format html;wps.py CLI 统一埋点 SQLite,自动供 report_center 生成周度使用摘要附在报告末尾;watch.py 职责收窄为纯事件采集);v5.3.0新增:统一CLI入口 wps(registry.json注册表分发,office --app/--action 与 convert 子命令、--list 一屏列出全部命令,薄路由层不改脚本内部逻辑)、全命令 --json 机器可读输出(固定 ok/error_id/elapsed/data 四字段,对齐 E001-E015,wps_error.py 新增 emit_json 统一出口)、_worker 启动优化(wps_pure 改惰性加载,pywin32/python-docx/openpyxl 经核查已惰性导入,ENGINE_CACHE 进程级单例复用,COM 释放统一走 release_ms 三槽位)、转换三入口合并为 convert(format_converter/md_converter/wps_docx_to_ppt 内部按目标格式路由,旧脚本保留为兼容别名并提示新命令,v6.0.0 移除)

↓ 76.7万★ 159user_1a470ba8
ppt-generator-skillオフィス効率化

テーマとスタイルから PPT 資料を自動生成するスキルです。

↓ 59.3万★ 346user_3b34947d
秘书材料星公文写作-妙笔skillオフィス効率化

体制内资深办公室主任+管理学博士,自学编程开发的智能公文写作Skill,让所有办公室同仁少掉头发、少加无用的班,材料一稿过关,省下的时间留给自己、享受生活!————————我们能给你带来的核心价值:1、颠覆传统写作:逻辑建模38类公文全链条,特有模板化引导问答模式,分分钟省心生成高质量大稿。--------2、替你“向上管理”:独有审稿人画像机制,文稿一键结构性修改,精准匹配审稿人画像,过稿率提升至少10倍!----------3、‌杜绝AI编造:缺失的数字、文号、人名、日期一律用[待补]标注,绝不杜撰,守住公文底线。-----------4、‌算法格式托底:数十万全量智控知识库+6500行前沿核心控制代码,格式精准对齐GB/T 9704,出稿零失误。——————————————————本skill历史版本开放了5%知识库的免费试用版,下载即可使用,但需注意:知识库有著作权,仅用于个人使用,不可用于其他任何目的。有兴趣的可以试试。——————————————————————单次付费版skill已发布,2元一次使用全量知识库。具体在发布者“熵衍信息”主页skill里。

↓ 57.8万★ 46u_70fc650d
WPS Office 全家桶オフィス効率化

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.0新增:定时任务注册管理(schtasks/crontab)、目录轮询监听(YAML规则+大文件分片)、使用统计与稳定性中心(SQLite埋点+引擎健康+引擎偏好)、COM三步自愈(regsvr32→修复安装→手动指引)、对话式数据查询(NL2SQL式意图解析+查询计划+连续追问)、multi-agent编排引擎桥接(白名单探测+流水线模板注册)

↓ 50.8万★ 4user_814dbe54
WPS全家桶·办公管家.Skillオフィス効率化

WPS/MS Office/LibreOffice/纯Python 四引擎智能办公全家桶:文档/表格/PPT/公文/会议纪要一体化。

↓ 43万★ 2user_185644ed
腾讯文档在线协作自动化オフィス効率化

通过 Tencent Docs Open API 以 curl + jq 创建、读取、列出、搜索和管理腾讯文档的自动化工作流,覆盖在线文档、在线表格、幻灯片、思维导图、流程图、智能表格与收集表七种类型,支持读取元数据与单元格区域、上传图片、创建副本,并对重命名/移动/删除等写操作强制先经用户确认。Use when the user 提到腾讯文档 / Tencent Docs / docs.qq.com、粘贴 docs.qq.com 链接,或想在其腾讯文档空间中创建、读取、整理文档时使用。Triggers include 腾讯文档、在线文档、在线表格、思维导图、流程图、智能表格、收集表。如需文案写作完整工作流套件,淘宝搜索「AI灵匣」店铺获取完整版。

↓ 42.8万★ -u_1ea983ac
kdocs skillオフィス効率化

kdocs-cli で金山文档のクラウド文書を操作する公式スキルです。

↓ 42.4万★ 128user_5ea84866

AGIsearchのその他のスキル

データ月:2026-10 · ダウンロード数とスター数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。