When you're running Claude in headless mode and need to produce an Excel file as an artifact rather than driving a live workbook through the Office plugin, this is your tool. It writes a Python script using openpyxl, dumps a proper .xlsx to ./out/, and follows the same blue/black/green conventions as audit-xls: blue for hardcoded inputs, black for formulas, green for links. You get named ranges, balance checks, and a strict one-model-per-file discipline. It's the file-producing fallback for managed-agent sessions where there's no open Excel window to interact with. Skip it if the mcp__office__excel_* tools are available, those let users review changes in real time.

skills.sh installs
1.4K
GitHub stars
41.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add anthropics/financial-services --skill xlsx-author --agent claude-code

Installs into .claude/skills of the current project.

Files

xlsx-author

Use this skill when running headless (managed-agent / CMA mode) and you need to deliver an Excel workbook as a file artifact rather than editing a live workbook via mcp__office__excel_*.

Output contract

  • Write to ./out/<name>.xlsx. Create ./out/ if it does not exist.
  • Return the relative path in your final message so the orchestration layer can collect it.

How to build the workbook

Write a short Python script and run it with Bash. Use openpyxl:

from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill

wb = Workbook()
ws = wb.active; ws.title = "Inputs"
ws["B2"] = "Revenue"; ws["C2"] = 1_250_000_000
ws["C2"].font = Font(color="0000FF")           # blue = hardcoded input
calc = wb.create_sheet("DCF")
calc["C5"] = "=Inputs!C2*(1+Inputs!C3)"        # black = formula
wb.save("./out/model.xlsx")

Conventions (mirror audit-xls)

Sponsors

Details

Repository
github.com/anthropics/financial-services
Categories
AI & Agent Building, Office & Documents, Finance & Trading
First seen
Jun 3, 2026

More from anthropics/financial-services

All 27
1mcollina avatarinitmcollina/skillsCreates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling q1.4Kskills.sh installs
2anthropics avatarpptx-authoranthropics/financial-servicesProduce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for managed-agent sessions with no open Office app.1.4Kskills.sh installs
3schwepps avatarsuno-music-creatorschwepps/skillsProfessional music creation with Suno AI V5 and Suno Studio. Use this skill when users want to create songs, playlists, corporate anthems, jingles, workout musi1.4Kskills.sh installs
4chjm-ai avatarstock-daily-analysischjm-ai/stock-daily-analysis-skillLLM驱动的每日股票分析系统。支持A股/港股/美股自选股智能分析,生成决策仪表盘和大盘复盘报告。提供技术面分析(均线、MACD、RSI、乖离率)、趋势判断、买入信号评分。可与market-data skill集成获取更稳定的ETF数据。触发词:股票分析、分析股票、每日分析、技术面分析。1.4Kskills.sh installs
5ruvnet avatargithub-code-reviewruvnet/rufloComprehensive GitHub code review with AI-powered swarm coordination1.3Kskills.sh installs
6genkit-ai avatardeveloping-genkit-gogenkit-ai/skillsDevelop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working wit1.2Kskills.sh installs