Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Read, write, and analyze tabular data with schema memory, format preservation, and multi-platform support.
Read, write, and analyze tabular data with schema memory, format preservation, and multi-platform support.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
User needs spreadsheet operations: reading data, writing cells, analyzing tables, generating reports, or tracking structured information across Google Sheets, Excel, or CSV files.
Memory lives in ~/spreadsheet/. See memory-template.md for setup. ~/spreadsheet/ memory.md # Preferences, recent sheets, format rules projects/ # Per-project schemas and configs {name}.md # Sheet IDs, columns, formulas templates/ # Reusable structures exports/ # Generated files
TopicFileMemory setupmemory-template.mdGoogle Sheets APIgoogle-sheets.mdExcel operationsexcel.mdCSV handlingcsv.md
This skill ONLY: Reads/writes spreadsheets user explicitly requests Stores schemas and preferences in ~/spreadsheet/ Processes files user provides This skill NEVER: Accesses sheets without user request Stores passwords, API keys, or sensitive financial data Modifies files outside ~/spreadsheet/ or user paths
All data stored in ~/spreadsheet/. Create on first use: mkdir -p ~/spreadsheet/{projects,templates,exports}
This skill NEVER modifies its own SKILL.md. All user data stored in ~/spreadsheet/ only.
On first access to any sheet: Document columns (name, type, sample) Save to projects/{name}.md Reference schema in future ops
SituationActionUpdating cellsPreserve existing formatWriting numbersMatch user's locale (1,000.00 vs 1.000,00)Writing datesUse user's preferred formatWriting formulasNever overwrite unless asked
Row CountApproach<1000Load fully1000-10000Sample + targeted queries>10000Paginate, warn before loading
Google Sheets - if API configured Excel (.xlsx) - local files, use openpyxl CSV - universal fallback
EventActionNew sheet accessedAdd ID + schema to memoryUser corrects formatSave preferenceColumn renamedUpdate project schema
Truncating without warning - Always confirm before loading >1000 rows Losing formulas - Use data_only=False in openpyxl, read formulas separately Schema drift - Re-verify if last access >7 days Rate limits - Batch Google Sheets requests, max 100/100s Encoding - Default UTF-8, check for BOM on European files Empty cells - Google API omits them; pandas fills with NaN
Data access, storage, extraction, analysis, reporting, and insight generation.
Largest current source with strong distribution and engagement signals.