Skip to content
cccskills
FreePublished on GitHub

office-script-expert

Office Scripts (Excel Online / Microsoft 365) development expert skill. Covers platform limitations, ExcelScript API patterns, testing strategy (lib + Vitest), and 13 real-world bug patterns discovered during production development. Trigger words: Office Scripts, ExcelScript, Excel Online, Office Script development, TypeScript Excel, Excel automation, CalculateRequirements, ImportCsvData

The English summary is being prepared. Showing the original description.

Works withExcel
See how to install

Files included (6)

  • SKILL.md6.6 KB
  • assets/implementation_checklist.md4.5 KB
  • references/common_bug_patterns.md12.1 KB
  • references/excel_api_patterns.md8.4 KB
  • references/platform_limitations.md4.2 KB
  • references/testing_strategy.md5.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Office Scripts Expert Skill

When to Use

  • Writing or reviewing Office Scripts (TypeScript for Excel Online)
  • Debugging runtime errors in Office Scripts
  • Setting up testable architecture for Office Scripts projects
  • Understanding ExcelScript API patterns and limitations
  • Migrating VBA macros to Office Scripts
  • Optimizing scripts to stay within 120-second timeout

Prerequisites

  • Microsoft 365 subscription with Excel Online access
  • Office Scripts enabled for the tenant (admin setting)
  • Node.js + npm (for local testing with Vitest)
  • TypeScript knowledge (Office Scripts use a TypeScript subset)

Overview

Office Scripts are TypeScript-based automation scripts for Excel on the web (Microsoft 365). They are fundamentally different from VBA and Power Automate:

AspectOffice ScriptsVBAPower Automate
LanguageTypeScript (subset)VBALow-code / expressions
RuntimeServer-side (Excel Online)Client-side (Desktop)Cloud service
Module systemNone (no import/export)ModulesConnectors
External libsNot availableCOM referencesConnectors
Timeout120 secondsNone30 min (premium)
TestingIndirect (lib extraction)ManualManual

Architecture Pattern: lib/ Extraction + Inline

Because Office Scripts cannot use import, the project uses a dual-file approach:

office_scripts/
  lib/                      # Canonical, testable source (ES modules)
    types.ts                # Interface definitions
    rounding.ts             # Rounding functions (export)
    prep-calculator.ts      # Prep calculation logic (export)
    ingredient-calculator.ts # Ingredient calculation logic (export)
    order-calculator.ts     # Order lot calculation (export)
    csv-parser.ts           # CSV parsing and header normalization (export)
  __tests__/                # Vitest unit tests
    rounding.test.ts
    prep-calculator.test.ts
    ingredient-calculator.test.ts
    order-calculator.test.ts
    csv-parser.test.ts
  CalculateRequirements.ts  # Main script (lib/* functions INLINED)
  ImportCsvData.ts          # Import script (lib/* functions INLINED)

Key rule: Edit lib/*.ts first, run tests, then copy the updated functions into the main scripts with // INLINED: lib/*.ts markers.

6 Critical Platform Constraints (P1-P6)

IDConstraintImpactWorkaround
P1No import/exportCannot share code between scriptsInline with markers
P2No external librariesNo lodash, date-fns, etc.Write from scratch
P3Map/Set for..of may failRuntime errors on iterationArray.from().forEach or indexed loop
P4120-second timeoutLarge datasets may failBatch processing, minimize API calls
P5console.log limitedNo persistent loggingUse cell writes for debug output
P6TypeScript subsetSome TS features unavailableTest in Office Scripts editor

See: references/platform_limitations.md

Reference Guide

Load these files based on your current task:

SituationReference to Load
Writing ExcelScript API code (read/write cells, sheets)references/excel_api_patterns.md
Debugging or reviewing existing codereferences/common_bug_patterns.md
Setting up or running testsreferences/testing_strategy.md
Understanding runtime constraintsreferences/platform_limitations.md
Before deploying / code reviewassets/implementation_checklist.md

Quick Reference Table

TaskPatternReference
Read sheet datagetUsedRange().getValues() + header index lookupexcel_api_patterns.md #1
Write results to sheetgetRangeByIndexes().setValues()excel_api_patterns.md #2
Protect/unprotect sheetunprotect() -> write -> protect()excel_api_patterns.md #3
Parse CSV inputDual-mode: single-cell text vs cell gridexcel_api_patterns.md #7
Section-based sheet parsingcurrentSection + currentHeaders state machineexcel_api_patterns.md #6
Clear data without destroying headersPre-locate section positions, clear data rows onlyexcel_api_patterns.md #8
Convert Excel datesexcelDateToJsDate(serial)excel_api_patterns.md #4
Sheet name with spaces in formulasQuote: 'Sheet Name'!A1excel_api_patterns.md #5
Iterate Map/SetArray.from(map.entries()) + indexed for loopplatform_limitations.md P3
Rounding to match PythonroundHalfEven2 / roundUp2 / roundUp4 / roundDown4excel_api_patterns.md #9
Test pure logiclib/*.ts with Vitesttesting_strategy.md
Pre-deploy reviewImplementation checklistimplementation_checklist.md

Workflow

  1. Understand requirements — Identify what data to read/write, which sheets, and any automation triggers
  2. Check platform constraints — Review P1-P6 constraints; confirm no external libraries needed
  3. Design with lib/ extraction — Write pure logic in lib/*.ts for testability
  4. Implement and test locally — Use Vitest to test lib/*.ts functions
  5. Inline into main script — Copy tested functions into .ts script with // INLINED: markers
  6. Test in Excel Online — Run the script in the Office Scripts editor
  7. Review with checklist — Use assets/implementation_checklist.md before deployment

Resources

TypePathPurpose
Referencereferences/platform_limitations.md6 critical platform constraints
Referencereferences/excel_api_patterns.mdExcelScript API patterns and examples
Referencereferences/common_bug_patterns.md13 real-world bug patterns
Referencereferences/testing_strategy.mdlib extraction + Vitest setup
Assetassets/implementation_checklist.mdPre-deployment review checklist

Output

This is an advisory/knowledge skill. Output is conversational guidance — no files are generated. The skill provides:

  • Code patterns and examples for Office Scripts development
  • Debugging assistance and bug pattern identification
  • Architecture recommendations for testable code
  • API usage guidance based on reference documentation

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

AI(LLM)が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン(視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー)を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 (バランスを崩す・客観を崩す・論理を崩す)でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.

The English summary is being prepared. Showing the original description.

takusaotome/claude-skills-library10Updated Oct 5, 2026

See all skills by takusaotome

Report a problem with this skill