From valuation-reviewer
Generates .xlsx files on disk via Python/openpyxl scripts for headless agent sessions without live Excel. Uses Inputs tab, formula conventions (blue/black/green), named ranges, and Checks tab.
How this skill is triggered — by the user, by Claude, or both
Slash command
/valuation-reviewer:xlsx-authorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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_*`.
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_*.
./out/<name>.xlsx. Create ./out/ if it does not exist.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")
audit-xls)If mcp__office__excel_* tools are available (Cowork plugin mode), use those instead — they drive the user's live workbook with review checkpoints. This skill is the file-producing fallback for headless runs.
npx claudepluginhub anthropics/financial-services --plugin valuation-reviewerGenerates .xlsx files on disk via Python/openpyxl scripts for headless agent sessions without live Excel. Uses Inputs tab, formula conventions (blue/black/green), named ranges, and Checks tab.
Enforces financial model formatting and formula construction rules for .xlsx files, including color coding, number format, and documentation standards.
Creates, reads, and modifies Excel spreadsheets (.xlsx, .xlsm, .csv, .tsv) with formulas, formatting, and data analysis. Includes financial modeling standards for zero-error delivery.