Skills Explorer Add Skills

xlsx

An agent skill by anthropics, from anthropics/skills. Tags: anthropic, debugging, documents, office, spreadsheets.

What it does

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add anthropics/skills --skill xlsx

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/anthropics/skills
cp -r skills/skills/xlsx ~/.claude/skills/xlsx

Safety box score

Grade C, moderate risk: 30 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill edits, validates, and recalculates spreadsheet files by running LibreOffice and related native tools on the local machine. The main risks are in-place workbook rewriting, possible loss of external links when forced, and the fact that it may install missing Python dependencies from the network.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)It launches native programs (`soffice`, `git`, and `gcc`) and even builds a shared library at runtime in `scripts/office/soffice.py` and `scripts/recalc.py`.
Network access2 (moderate)`SKILL.md` explicitly allows fallback `pip install` when imports or `markitdown` are missing, which can fetch code from package indexes.
Filesystem reach2 (moderate)The skill rewrites the target workbook in place and `validate.py --auto-repair` says it "Modifies the input in place"; `recalc.py` can also overwrite the original file.
Secrets & credentials0 (none)The code only handles workbook XML, temp files, and Office process state; it does not read keychains, `.env` files, browser sessions, or other credential stores.
Privilege & persistence1 (low)It does not request sudo or persistent OS changes, but `scripts/office/soffice.py` sets `LD_PRELOAD` and runs LibreOffice under a custom profile.
Instruction hijack surface0 (none)There is no fetched prompt content, hidden instruction text, or guidance to bypass confirmations; the files are ordinary tool code and spreadsheet instructions.
Irreversible actions0 (none)It does not send messages, publish, pay, deploy, or delete remote resources; its effects stay local to spreadsheet files and validation processes.
Transparency1 (low)Most code is readable, but `scripts/office/soffice.py` generates and compiles `_SHIM_SOURCE` into a temp `.so` at runtime, so some behavior is only revealed after execution.

Before installing

Rated 2026-10-20 by an automated review of 14 files from the skill's repository.

Source

Repository
anthropics/skills (all skills from this repository)
Path
skills/xlsx/SKILL.md
Branch
main
Updated
2026-09-19