Data & Analysis ✓ Anthropic · Official xlsx-generationopenpyxlfinancial-modelingheadless-automationspreadsheet-audit

Headless Excel Workbook Builder

Generate reviewable .xlsx artifacts in managed-agent sessions without an open Office application.

FollowSkills review · FSRS-2.0
Not recommended
52/ 100 5-point scale 2.6 / 5
Trust16 / 25 · 3.2/5

The skill restricts output to ./out/<name>.xlsx, requires no network, credentials, or external systems, and says not to append to an existing workbook; this provides some scope control. Points are deducted because user confirmation, sensitive-financial-data handling, overwrite/rollback controls, and pinned dependency requirements are absent.

Reliability8 / 20 · 2.0/5

The instructions and example are broadly consistent: use Python, Bash, and openpyxl to create and save a workbook, while directing users to Excel tools in Cowork mode. Points are deducted because dependency availability is not checked, abnormal inputs and save failures lack handling, and diagnostic failure feedback is unspecified; static review cannot support a score above 10.

Adaptability10 / 15 · 3.3/5

The audience, output path, headless context, live-workbook boundary, and non-use condition are clearly stated. Points are deducted because input formats, failure boundaries, semantic trigger conditions, and Chinese-language support are unspecified, as is adaptation to mainland-China network conditions.

Convention8 / 15 · 2.7/5

The document is clearly layered and includes an output contract, construction example, formatting conventions, and usage boundary; the repository supplies Apache-2.0 licensing, official Anthropic provenance, CI validation, and contribution guidance. Points are deducted because the skill itself lacks versioning, changelog, named maintenance responsibility, installation/dependency instructions, FAQ, detailed limitations, and an update path.

Effectiveness6 / 15 · 2.0/5

The skill directly addresses producing a collectable .xlsx artifact when no Office application is available, with a concrete minimal example and financial-model conventions. Points are deducted because it does not verify workbook output, formula behavior, or check-tab completeness; the example still requires human review, and comparative benefit over manual scripting or alternatives is not evidenced. Static calibration limits this to 7.

Verifiability4 / 10 · 2.0/5

The repository includes real CI configurations for plugin validation and secret scanning, and the skill provides a concrete code pattern that is auditable. Points are deducted because there are no committed xlsx-author key-path tests, sample artifacts, third-party execution records, or corroborating sources; static calibration limits this to 5.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 4aa51ed3d379
Before you use it
  • Pin and verify Python and openpyxl versions before use because environment differences may reduce reproducibility.
  • The skill does not prove that formulas calculate, balance checks pass, or the workbook matches a business template; human review is required before delivery.
  • Overwrite behavior, partial files after failure, and recovery procedures for ./out/ are unspecified; callers must provide isolation, access control, and cleanup for sensitive financial data.
  • Chinese text, locale-specific formats, dates, and formula localization are not addressed; Chinese users should validate compatibility first.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

xlsx-author creates Excel workbooks as files on disk instead of editing a live Excel workbook. It targets headless managed-agent or CMA sessions and requires output under ./out/<name>.xlsx. The skill specifies color conventions for hardcoded inputs, formulas, and links, along with Inputs, calculation, and Checks sheet practices. It fits workflows that need structured spreadsheet deliverables when no Office application is available.

Creates ./out/ when necessary, writes and runs a short Python script, uses openpyxl to create worksheets, cells, formulas, and styles, and saves the result as ./out/<name>.xlsx. It specifies blue for hardcoded inputs, black for formulas, and green for links to another sheet or file. Calculation cells must contain formulas rather than hardcoded values; inputs belong on an Inputs tab; and values referenced from a deck or memo should use named ranges. A Checks tab should surface balance-sheet, cash-flow, and related checks as TRUE/FALSE results.

  1. A managed-agent workflow needs to deliver a financial model as an Excel file without an open Office application.
  2. A financial analyst needs separate input, calculation, and validation areas in a generated workbook.
  3. A model builder needs visible color coding for hardcodes, formulas, and cross-sheet links.
  4. A reviewer needs workbook-level balance checks that clearly surface TRUE or FALSE.
  5. An orchestration pipeline needs to collect a generated .xlsx artifact from a known relative path.

Pros & cons

Pros
  • Defines a precise, collectible output path for .xlsx artifacts.
  • Supports fully headless workbook generation.
  • Provides review-oriented conventions for inputs, formulas, links, named ranges, and checks.
  • Uses the widely used Python openpyxl library.
Limitations
  • Requires Python, Bash, and openpyxl; the source does not specify versions.
  • The source provides no test suite, error-handling design, or recovery workflow.
  • It is a file-producing fallback; when mcp__office__excel_* tools are available, the skill directs users to use live-workbook operations instead.
  • The source does not document testing coverage for complex formulas, external links, or Excel compatibility.

How to install

Add the repository in Claude Cowork through Settings → Plugins → Add plugin, then paste https://github.com/anthropics/financial-services and select the relevant plugin; or in Claude Code run: claude plugin marketplace add anthropics/financial-services. The README does not provide a separate installation command for xlsx-author. The skill is located at plugins/agent-plugins/statement-auditor/skills/xlsx-author/SKILL.md.

How to use

In a headless, managed-agent, or CMA session, request an Excel file, for example: “Create an .xlsx financial model with Inputs, calculation, and Checks sheets, and save it as ./out/model.xlsx.” The SKILL.md does not define a formal trigger syntax or input schema. The final response should return the relative path ./out/<name>.xlsx.

Compared to similar skills

The SKILL.md distinguishes xlsx-author from mcp__office__excel_* live workbook operations: xlsx-author is for headless file generation, while those tools are intended for live workbook editing in Cowork plugin mode.

FAQ

Does it modify an open Excel workbook directly?
No. It targets headless sessions and writes a .xlsx artifact under ./out/.
Is openpyxl required?
The SKILL.md specifies openpyxl and provides a Python example using it.
Where must the output file go?
It must be written to ./out/<name>.xlsx, creating ./out/ if needed.
Does it provide investment, accounting, or tax advice?
The README states that repository outputs are not investment, legal, tax, or accounting advice and require qualified professional review.

More skills from this repository

All from anthropics/financial-services

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Builder

Populate and validate linked income statement, balance sheet, and cash flow models with formulas.

Data & Analysis ✓ Anthropic · Official

Spreadsheet Auditor

Checks spreadsheet formulas, errors, and financial-model integrity.

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Builder

Complete existing three-statement templates with linked formulas, projections, scenarios, and audit checks.

Data & Analysis ✓ Anthropic · Official

Comparable Company Valuation

Build institutional-grade peer valuation analyses with operating metrics, trading multiples, and statistical benchmarks in spreadsheets.

Data & Analysis ✓ Anthropic · Official

Competitive Landscape Analyst

Turn competitive research into an approved, comparable market landscape deck.

Data & Analysis ✓ Anthropic · Official

Earnings Update Researcher

Turn quarterly results into an institutional-style update focused on beats, estimate changes, valuation, and thesis impact.

Data & Analysis ✓ Anthropic · Official

Sector Landscape Research

Structure industry dynamics, competition, valuation, and investment themes in one research workflow.

Productivity & Collaboration ✓ Anthropic · Official

PE Investment Committee Memo Writer

Turns diligence, financial analysis, and deal terms into a structured memo for private equity investment committee approval.

Data & Analysis ✓ Anthropic · Official

Excel Data Cleaning Assistant

Clean inconsistent spreadsheets before analysis.

Data & Analysis ✓ Anthropic · Official

Financial Deck Refresh

Update financial figures across an existing presentation while preserving its formatting and structure.

Writing & Content ✓ Anthropic · Official

IC Memo Drafting

Turns diligence and financial inputs into a structured IC memo.

Data & Analysis ✓ Anthropic · Official

Financial Model Auditor

Find spreadsheet formula errors and test financial-model integrity before review.

Automation & Ops ✓ Anthropic · Official

Reconciliation Break Tracer

Trace ledger breaks to source entries and state the operational root cause.

Automation & Ops ✓ Anthropic · Official

KYC Intake Parser

Turn onboarding packets into structured KYC data ready for screening.

Data & Analysis ✓ Anthropic · Official

Audit XLS: Spreadsheet Model Review

Systematically checks spreadsheet formulas, errors, and financial-model integrity issues.

Data & Analysis ✓ Anthropic · Official

General Ledger Roll-Forward

Connects a balance-sheet account’s opening balance to its period-end GL balance for close packages and audit support.

Data & Analysis ✓ Anthropic · Official

Investment Banking Pitch Deck Filler

Populate existing investment banking PowerPoint templates with validated data from Excel, CSV, and other source files.

Data & Analysis ✓ Anthropic · Official

Three-Statement Model Filler

Complete and validate integrated three-statement templates with formulas, linkages, and audit checks.

Data & Analysis ✓ Anthropic · Official

Financial Model Audit

Systematically checks spreadsheet formulas and model integrity.

Data & Analysis ✓ Anthropic · Official

GL–Subledger Reconciliation

Reconcile general ledger and subledger data, expose breaks, and suggest likely causes for investigation.

Related skills