Editorial profile
The source-available spreadsheet skill covers XLSX, XLSM, CSV, and TSV work with formulas, formatting, charts, cleanup, recalculation, and verification. It emphasizes editable models and source documentation rather than hard-coded summary values.
Where Spreadsheets fits
The useful question is not whether this agent skill can be installed. It is whether its scope matches a named workflow, keeps the authoritative system clear, and gives a reviewer enough evidence to trust the result.
- KPI workbooks
- Forecasts and operating models
- Cleaning and restructuring tabular exports
Documented capabilities
These are the practical capabilities described by the current public source. Confirm the exact tool surface, account limits, and enabled permissions in the client you plan to use.
- Create and edit formatted workbooks
- Build formulas, charts, and reusable models
- Recalculate and check outputs for formula errors
Setup outline
Treat setup as a small integration project. Use a dedicated test identity, begin with the narrowest access available, and record who owns upgrades and credential revocation.
- Install the document-skills bundle or copy the XLSX skill
- Make its spreadsheet and recalculation dependencies available
- Provide exact sheet names, inputs, formulas, and output expectations
What to check before adoption
Product documentation normally shows the happy path. The items below are the constraints or open questions most likely to affect a business rollout.
- The skill is source-available, not open source.
- A clean recalculation does not prove that a formula uses the correct business logic.
Botfinder's take
Spreadsheets has the advantage of first-party provenance: the publisher controls the underlying product and its integration surface. That reduces one layer of ambiguity, but it does not remove the need to test permissions, failure handling, output quality, and the complete data path.
Start with a read or draft workflow where a person can compare the result with the source system. Add mutation only after the team can explain approvals, duplicate protection, partial failures, and recovery without relying on the model to infer whether a write succeeded.