Data & Analysis ✓ Anthropic · Official xlsx-generationopenpyxlspreadsheet-exportheadless-workflowfile-artifactpython-scripting

XLSX Author

Generate a .xlsx file directly in headless sessions.

FollowSkills review · FSRS-2.0
Not recommended
47/ 100 5-point scale 2.4 / 5
Trust14 / 25 · 2.8/5

The skill limits output to a local ./out/<name>.xlsx artifact and uses a headless workflow without requiring external services or broad permissions. It lacks user confirmation, sensitive-data guidance, overwrite protection, rollback, and explicit data-flow disclosure, so points are deducted.

Reliability8 / 20 · 2.0/5

The instructions, example, output path, and workbook conventions are internally coherent. However, openpyxl availability and version are unspecified, and there is no input validation, exception handling, failure feedback, or static evidence of reproducible key-path tests; deductions apply and the static ceiling is respected.

Adaptability8 / 15 · 2.7/5

The target scenario is clear: managed-agent/CMA sessions without an open Office application, with a stated non-fit case when live Excel tools are available. Trigger precision, input boundaries, complex-workbook limitations, and Chinese-environment support are insufficiently documented, so points are deducted.

Convention8 / 15 · 2.7/5

The document is concise and layered around an output contract, construction method, conventions, and non-use case. Repository-level Apache-2.0 licensing and CI are present, but the skill lacks its own versioning, changelog, maintenance owner, update path, FAQ, and troubleshooting guidance, so points are deducted.

Effectiveness6 / 15 · 2.0/5

The skill plausibly produces a directly collectable .xlsx artifact and provides useful modeling conventions for inputs, formulas, links, and checks. There is no committed representative output, completeness validation, formula-calculation compatibility guidance, or comparative-benefit evidence, so the score remains moderate and within the static limit.

Verifiability3 / 10 · 1.5/5

The skill text and repository CI are auditable, and CI validates plugin structure. There is no committed test suite, execution log, or third-party reproduction evidence covering the xlsx-author key paths, so only limited credit is justified.

Evidence confidence:Low Reviewed Jul 19, 2026 Reviewed revision 4aa51ed3d379
Before you use it
  • Execution assumes that openpyxl is available, but no version, installation, or dependency check is documented.
  • The skill specifies file creation but does not ensure formula recalculation, external-link integrity, or correctness for complex workbooks; human review is required, and overwrite risk should be checked.
  • The repository CI primarily validates plugin structure and does not establish that this skill generates correct workbooks.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

This skill is for headless managed-agent sessions that need an Excel workbook as a file artifact. It writes the workbook to local disk at `./out/<name>.xlsx` instead of driving an open Excel workbook. The skill body shows a Python example built with `openpyxl`, including formulas and formatting. It fits workflows where you need a deliverable spreadsheet and there is no live Office app to control.

Creates ./out/ if needed and saves a .xlsx file there; uses Python and openpyxl to build a workbook; writes worksheets, cell values, formulas, and font styling; returns the relative output path for collection by the orchestration layer.

  1. You need to hand back an Excel file from a managed-agent run, not edit a live workbook
  2. You want to generate a spreadsheet model with formulas and formatting from Python
  3. There is no open Office app available, so the workflow must produce a file artifact
  4. You need the output saved under `./out/` for downstream retrieval

Pros & cons

Pros
  • Produces a real `.xlsx` file artifact
  • Straightforward dependency set: Bash, Python, and openpyxl
  • Well suited to headless sessions without a live Excel app
Limitations
  • Only the file-generation path is documented; there is no advanced templating or validation workflow here
  • It is not the right fit when you need to control an already-open Excel workbook
  • No built-in test or error-handling guidance is shown

How to install

Place the skill at plugins/agent-plugins/model-builder/skills/xlsx-author/SKILL.md. The repository README says the collection can be deployed as a Claude Cowork plugin or through Claude Managed Agents.

How to use

Write a short Python script using openpyxl, then save the workbook to ./out/<name>.xlsx. The example in the skill saves ./out/model.xlsx; return that relative path in your final response.

Compared to similar skills

Compared with live-workbook control, this skill uses a file-output workflow. The README also says to use mcp__office__excel_* tools when they are available; this skill is the headless fallback.

FAQ

Does it edit an open Excel workbook?
No. It generates a workbook file on disk.
Where does the output go?
`./out/<name>.xlsx`, with the relative path returned for collection.
What does it depend on?
The source explicitly shows Bash, Python, and `openpyxl`.
When should I not use it?
If live `mcp__office__excel_*` tools are available, use those instead of the file-producing fallback.

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