Guidelines and utility knowledge for working with formula-driven Excel workbooks and openpyxl.
Guidelines and utility knowledge for working with formula-driven Excel workbooks and openpyxl.
npx skills add https://github.com/cas-team-analyst/team-analyst --skill excel-formulas复制此命令并粘贴到 Claude Code 中以安装该技能
| name | excel-formulas |
| description | Guidelines and utility knowledge for working with formula-driven Excel workbooks and openpyxl. |
Core principle: Inject live Excel formulas (not hard-coded values) so workbooks recalculate when actuaries change selections.
Critical pattern: Generate formula-driven Excel + JSON replica (openpyxl can't evaluate formulas, so JSON stores evaluated data for downstream scripts).
Key utilities: Use rewrite_formula_sheet_refs() from modules/formulas.py when aggregating sheets → Best Practices
This codebase relies heavily on Excel workbooks not just for displaying outputs, but as live, interactive dashboards. To support this, generated workbooks must inject live Excel formulas rather than hard-coded values wherever a value can be derived.
data_only=True): Openpyxl cannot evaluate Excel formulas. If you read a workbook with data_only=True before it has been opened and saved in Excel by a human, all formula-driven cells will return None.selections/chainladder-incurred_loss.json) for downstream consumption.='Incurred Loss'!B2) must be dynamically rewritten if the sheet names change (e.g. ='CL - Incurred Loss'!B2). Use the rewrite_formula_sheet_refs utility in modules/formulas.py.Actuarial reserving analysis workflow. Use when the user requests reserving. Do NOT use for peer review (separate skill exists).
Peer review of completed reserve analysis. Use after reserving-analysis workflow finishes. Do NOT use during initial analysis (separate skill exists).
Guidelines for creating formula-driven Excel workbooks with xlsxwriter. Inject live Excel formulas with cached values so workbooks display immediately and recalculate when actuaries change selections. Covers formula patterns, cross-workbook references, and shared formatting modules.
Get oriented with the TeamAnalyst plugin and explore available skills. Use when first getting started, checking what analysis capabilities are available, or surveying skills before beginning work. Trigger phrases "start", "get started", "what can you do", "help", "overview", "show skills".
View the base actuarial LDF selection logic used for chain-ladder selections. Use when an actuary wants to review or understand the selection framework, criteria, and diagnostic rules.
Guide for Python development in this project. Use any time you write Python.