excel-workbook

excel-workbook is a skill for Claude Code from adongwanai/learn-workbuddy. It costs 79 tokens per session (1,038 once invoked), scanned A, original, MIT.

A basic Excel workbook tool for creating, inspecting, editing, and checking .xlsx files. It supports worksheets, cells, simple formulas, dates, and basic formatting, but not macros, charts, pivot tables, or external workbook links.

In plain words
What is it for?
Use it to inspect workbooks, create tables with simple formulas, edit cells or rows, preserve existing content, and validate the resulting .xlsx file.
Why use it?
It lets you make controlled spreadsheet changes and verify the file structure without rebuilding untouched areas or overwriting the original by default.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect workbooks, create tables with simple formulas, edit cells or rows, preserve existing content, and validate the resulting .xlsx file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adongwanai/learn-workbuddy/excel-workbook
Install

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.

Any agent
npx skills add adongwanai/learn-workbuddy --skill excel-workbook
Clone the repo
git clone --depth 1 https://github.com/adongwanai/learn-workbuddy

Made for: Claude Code.

Wrote 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.

agentmods badge for excel-workbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/adongwanai/learn-workbuddy/excel-workbook/github.svg)](https://agentmods.dev/skills/adongwanai/learn-workbuddy/excel-workbook)
Your own site
<a href="https://agentmods.dev/skills/adongwanai/learn-workbuddy/excel-workbook"><img src="https://agentmods.dev/badge/skills/adongwanai/learn-workbuddy/excel-workbook/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for excel-workbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/adongwanai/learn-workbuddy/excel-workbook"><img src="https://agentmods.dev/badge/skills/adongwanai/learn-workbuddy/excel-workbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01038
Opus 5.5 $0.00032 $0.00415
Sonnet 5.5 $0.00016 $0.00208
Haiku 4.5 $0.00008 $0.00104

Measured 23d ago against content hash a06bd3678514, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

excel-workbook 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 23d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/workbook_tool.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/excel-workbook/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Excel 工作簿基础操作

当用户要求创建、检查、编辑或验证 .xlsx 文件时使用本 Skill。

支持范围

支持以下基础操作:

  • 检查工作簿、工作表、行列范围、公式、日期和合并单元格;
  • 创建包含表头、数据和简单公式的新工作簿;
  • 编辑单元格、追加行和基础数字格式;
  • 保留已有工作表、公式、日期、数据类型和未修改区域的基础样式;
  • 重新打开输出文件,验证关键内容;
  • 设置 Excel/WPS 打开文件时自动重算的标记。

当前版本只支持 .xlsx。不处理 .xlsm 宏、VBA、图表、数据透视表、 Power Query、外部工作簿引用或复杂财务模型。

工作原则

  1. 先检查,再修改。
  2. 默认不覆盖原文件;编辑时输入文件和输出文件必须是不同路径。
  3. 修改现有模板时,只改用户指定的单元格或区域,不重建整个工作簿。
  4. 日期、数字和公式要保持正确的数据类型。公式字符串被写入不等于公式已经计算。
  5. 修改后必须重新打开输出文件并验证。
  6. 没有 Excel、WPS 或 LibreOffice 重算结果时,不要声称公式结果已经验证。

工具脚本

脚本位于当前 Skill 的 scripts/workbook_tool.py:

python scripts/workbook_tool.py inspect input.xlsx
python scripts/workbook_tool.py create output.xlsx --spec spec.json
python scripts/workbook_tool.py edit input.xlsx output.xlsx --operations operations.json
python scripts/workbook_tool.py validate output.xlsx --expect expectations.json
python scripts/workbook_tool.py recalc output.xlsx

所有命令默认输出 JSON,便于继续检查和记录。

创建数据格式

create 的 spec 使用以下结构:

{
  "sheet": "销售数据",
  "headers": ["日期", "商品", "金额", "含税金额"],
  "rows": [
    [
      {"date": "2026-09-16"},
      "A",
      100,
      {"formula": "=C2*1.1"}
    ]
  ],
  "column_widths": {"A": 14, "C": 12, "D": 14}
}

日期使用 {"date": "YYYY-MM-DD"},公式使用 {"formula": "=..."}。

编辑数据格式

edit 的 operations 使用以下结构:

{
  "set_cells": [
    {"sheet": "销售数据", "cell": "C2", "value": 120},
    {"sheet": "销售数据", "cell": "D2", "formula": "=C2*1.1"},
    {"sheet": "销售数据", "cell": "A2", "date": "2026-09-17"}
  ],
  "append_rows": [
    {
      "sheet": "销售数据",
      "values": [{"date": "2026-09-18"}, "B", 80, {"formula": "=C3*1.1"}]
    }
  ],
  "number_formats": [
    {"sheet": "销售数据", "cell": "C2", "format": "#,##0.00"}
  ]
}

验证数据格式

validate 的 expectations 使用以下结构:

{
  "sheets": ["销售数据"],
  "cells": {
    "销售数据!C2": 120,
    "销售数据!D2": "=C2*1.1",
    "销售数据!A2": {"date": "2026-09-17"}
  },
  "required_formulas": ["销售数据!D2"]
}

重算边界

recalc 会先设置:

calcMode=auto
fullCalcOnLoad=true
forceFullCalc=true

Read the full file on GitHub · 135 lines

Files

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.

Changes

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.

  1. 23d ago First seen · 135 lines · 79 tokens per session scan A a06bd3678514

Subscribe to this mod's changes

excel-workbook is a skill published in the GitHub repository adongwanai/learn-workbuddy (437 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,038 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.