spreadsheets

原文涵盖的主题

• Spreadsheets
• Invariants
• Factual Profiling
• Tool Routing
• Workflow
• Generated Financial Artifacts

Handle tabular data with exact values, minimal diffs, recipient-scoped data handling, atomic writes, and structural validation. 1. Keep precision-sensitive amounts as strings and compute with decimal.Decimal or DuckDB DECIMAL(38, 18), never binary floats. 2. Touch only requested rows, columns, formulas, and formatting. Existing file conventions override house defaults. 3. For newly authored text tables, prefer TSV, UTF-8 without BOM, LF, one trailing newline, lowercase snakecase headers, ISO dates, . decimals, and - nulls. 4. Read unknown text tables with BOM-tolerant UTF-8. Never write a BOM. 5. Write in place atomically through a sibling temporary file, validate it, then replace the target. 6. Escape external cells beginning with =, +, or @. A bare - null is exempt. Formula-prefix cells in trusted authored data are observations, not proof of injection. 7. Treat transaction, bank, exchange, and tax data as user-owned. Use unredacted samples in internal agent reports when materially useful. For public or third-party disclosures, or when the user asks, use --redact-samples. Resolve helper paths from this SKILL.md. Profile unknown data before choosing a transformation tool: The JSON

这里只展示节选，请以完整原文和当前要求为准。