Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nimadorostkar/Claude-Skills-collection --skill spreadsheetsgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/spreadsheets)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/spreadsheets"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/spreadsheets/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/spreadsheets"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/spreadsheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01523 |
| Opus 5 | $0.00022 | $0.00762 |
| Sonnet 5 | $0.00009 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
spreadsheets scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spreadsheets
Purpose
Build and repair spreadsheets, including the ones that arrive with headers on row 7, merged cells, and three tables on one sheet. Most spreadsheet work is cleaning, not computing.
When to Use
- Creating a spreadsheet from data.
- Reading or extracting data from an existing workbook.
- Cleaning a messy file into something a machine can read.
- Adding formulas, formatting, or charts.
- Converting between tabular formats.
Capabilities
- Workbook generation: sheets, formulas, formatting, conditional formatting, charts.
- Reading, including files whose structure is not a clean table.
- Data cleaning: header detection, type coercion, deduplication.
- Formula construction, including cross-sheet references.
- Format conversion.
Inputs
- The data, or the source workbook.
- The intended audience: a human reading it, or a machine parsing it.
- Any formatting or template requirements.
Outputs
- A workbook with correct formulas and readable formatting.
- Or clean, typed, tabular data extracted from a messy source.
Workflow
- Inspect before parsing — Read the first thirty rows raw. Real spreadsheets have title rows, blank rows, merged headers, and notes in the margins. Assuming
header=0is how you end up with a DataFrame whose columns areUnnamed: 0. - Find the actual header row — The first row where every cell is non-empty and the row below it has consistent types.
- Coerce the types explicitly — Excel stores dates as numbers, numbers as text, and empty cells as several different things. Nothing is what it appears.
- Clean before computing — Trim whitespace, unify the null representations, drop the total row that got read as data.
- When writing for humans, format — Column widths, number formats, a frozen header row. An unformatted spreadsheet with a column of
1234567.891is not usable. - Verify the formulas calculate — A written formula is a string until a spreadsheet application evaluates it. Open the file and check.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 140 lines · 43 tokens per session scan A 4804efb26223
spreadsheets is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 1,523 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Excel工具
A guide for using Excel tools to read, write, and recalculate spreadsheet files. It includes a rule for treating the first row as data when a spreadsheet has no column headings.
excel-date-to-text
Scan all date columns in Excel and convert datetime values to user-specified text format (yyyymmdd, yyyy-mm-dd, yyyy/mm/dd, yyyy年mm月dd日, or any custom combination). Supports three output positions: insert new column on left, insert new column on right, or replace original column. New column headers can be customized…
excel-delete
A tool for deleting rows or columns from Excel spreadsheets. It checks whether formulas depend on the items being removed and supports deletion by row number, column name, or position.
excel-filter
A tool for filtering Excel spreadsheet rows by conditions such as matching text, dates, ranges, or empty cells. It can either keep matching rows and remove the rest, or remove matching rows and keep the rest.
excel-merge
A tool for combining multiple Excel files with the same column structure into one file.
excel-replace
A controlled way to replace values in Excel workbooks, including whole columns, rows, selected cells, formulas, or Python-based transformations. It first identifies the requested range and requires confirmation before overwriting content.