Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Excel / XLSX Spreadsheets · code-saurabh | DecimalAI

databy code-saurabh

Excel / XLSX Spreadsheets

code-saurabh/xlsx

Source code-saurabh/openskills ↗License MIT

Create, read, edit, and analyse Excel spreadsheet files (.xlsx, .xlsm, .xltx, .csv, .tsv).

SkillScore91Maintained

Automatic

Data Analyst pack

Last verified 8/4/2026

What it changes

Passed 19 of 21 test cases with the skill, and 14 of 21 without it.

Without skill68%

With skill91%

Checks it passed that the model alone missed

The formula cells use a black font color.
The hardcoded input cells use a blue font color.
The CLI command uses markitdown to read the excel file.

and 5 more in the full report

6 fixed14 passed either way1 still failing1 broke

Pass-rate lift: +23 pp
Tokens: +167%
Agent turns: 0%
Response time: -9%

Model gemini-3.6-flashMeasured 8/4/2026v120 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/code-saurabh-xlsx/SKILL.md https://app.decimal.ai/s/code-saurabh-xlsx/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add code-saurabh-xlsx, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/code-saurabh-xlsx/ and pins it in .decimal/skills.lock

decimalai skills add code-saurabh-xlsx

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/code-saurabh-xlsx/SKILL.md https://app.decimal.ai/s/code-saurabh-xlsx/SKILL.md

Raw file: /s/code-saurabh-xlsx/SKILL.md ↗ · machine-readable summary at /s/code-saurabh-xlsx.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

I need to quickly inspect the text contents and table structures of `q3_audit.xlsx` from the command line without opening Python or inspecting individual cell coordinates. How can I preview this file in the terminal?

What was checked, without and with the skill
Checked	Without skill	With skill
The CLI command uses markitdown to read the excel file.	Missed	Passed

case-04 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md359 linessingle file

Excel / XLSX Spreadsheets

A .xlsx file is a ZIP archive of XML. Work with it programmatically using openpyxl (formulas + formatting) or pandas (bulk data). Choose the right tool for the job and apply it precisely.

Task	Tool
Create or edit with formulas and formatting	`openpyxl`
Bulk data in/out, pivot analysis	`pandas` (`read_excel`, `to_excel`)
Quick read of content	`markitdown file.xlsx`
Reading both formulas AND cached values	Two `load_workbook` passes — see gotchas

openpyxl, pandas, and markitdown are typically pre-installed. Import directly. Only run pip install if an import fails.

Non-Negotiable Standards

Every spreadsheet delivered must meet these standards:

Professional font throughout. Arial or Calibri for data, Times New Roman for formal reports. No default Calibri 11 unless that is the existing convention.
Zero formula errors. Never ship while recalc shows errors. A #DIV/0!, #REF!, or #NAME? in a delivered file is a failure.
Use formulas, not hardcoded results. Write =SUM(B2:B9), not the Python-computed value. The sheet must recalculate when inputs change.
Follow the user's spec literally. Exact tab names, exact column headers, exact formula logic. Never redesign what was asked.
Document every assumption. Hardcoded numbers need a cell comment or adjacent label with the source. "Source: Company 10-K, FY2024, Page 45" is correct. Unexplained magic numbers are not.
Input cells need a legend. If you create a template for someone to fill in, add a legend naming which cells to edit and include one example row showing expected format.
Editing existing files: match conventions exactly. Find the designated input cells (usually distinguished by font color or fill). Write only there. Leave all existing formulas untouched.

Reading a Spreadsheet

import subprocess

# Quick content read (no cell coordinates — use for overview only)
result = subprocess.run(["markitdown", "file.xlsx"], capture_output=True, text=True)
print(result.stdout)

# Read into pandas (values only, no formulas)
import pandas as pd

Track record

Benchmark

19 / 21

test cases passed, vs 14 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

code-saurabh / openskills

xlsx/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Excel / XLSX Spreadsheets

Non-Negotiable Standards

Reading a Spreadsheet

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills