Claude Skill

xlsx

Extract data from Excel and CSV files

LLM Mart · 0 points · 16 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download axoviq-ai-synthadoc-synthadoc_skills_xlsx-8dee0ee.zip · 1 KB

axoviq-ai/synthadoc 1226 123 forks AGPL-3.0 Updated 5d ago

Part of axoviq-ai/synthadoc — 10 skills

Install

skills CLI npx skills add https://github.com/axoviq-ai/synthadoc/tree/main/synthadoc/skills/xlsx

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install axoviq-ai-synthadoc@llmmart

Git git clone https://github.com/axoviq-ai/synthadoc.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole axoviq-ai/synthadoc collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

XLSX Skill

Reads .xlsx files using openpyxl and .csv files using the stdlib csv module, returning all rows as comma-separated text.

Setup

pip install openpyxl

.csv files use only the Python standard library — no additional install required.

Standalone usage

import asyncio
from synthadoc.skills.xlsx.scripts.main import XlsxSkill

skill = XlsxSkill()

async def main():
    result = await skill.extract("/path/to/data.xlsx")
    print(result.text)      # all rows as comma-separated text
    print(result.metadata)  # {"rows": N, "sheets": N}  (xlsx only)

asyncio.run(main())

When this skill is used

Source path ends with .xlsx or .csv
User intent contains: spreadsheet, excel, csv

Files (synthadoc)

scripts

main.py 1.4 KB

# SPDX-License-Identifier: AGPL-3.0-or-later
# Copyright (C) 2026 Paul Chen / axoviq.com
import openpyxl
from synthadoc.skills.base import BaseSkill, ExtractedContent, SkillMeta


class XlsxSkill(BaseSkill):
    meta = SkillMeta(name="xlsx", description="Extract data from Excel and CSV files",
                     extensions=[".xlsx", ".csv"])

    async def extract(self, source: str) -> ExtractedContent:
        if source.endswith(".csv"):
            import csv
            rows = []
            with open(source, encoding="utf-8", newline="") as f:
                for row in csv.reader(f):
                    rows.append(", ".join(row))
            return ExtractedContent(text="\n".join(rows), source_path=source, metadata={})
        try:
            wb = openpyxl.load_workbook(source, read_only=True, data_only=True)
        except Exception as exc:
            raise ValueError(
                f"Cannot read '{source}' as an Excel file: {exc}. "
                "Ensure the file is a valid .xlsx (Office Open XML) document."
            ) from exc
        parts = []
        for name in wb.sheetnames:
            parts.append(f"## Sheet: {name}")
            for row in wb[name].iter_rows(values_only=True):
                parts.append(", ".join(str(c) for c in row if c is not None))
        return ExtractedContent(text="\n".join(parts), source_path=source,
                                metadata={"sheets": len(wb.sheetnames)})

__init__.py 0 B

requirements.txt 54 B

openpyxl
# csv is Python stdlib — no install needed

SKILL.md 1 KB

---
name: xlsx
version: "1.0"
description: Extract data from Excel and CSV files
entry:
  script: scripts/main.py
  class: XlsxSkill
triggers:
  extensions:
    - ".xlsx"
    - ".csv"
  intents:
    - "spreadsheet"
    - "excel"
    - "csv"
requires:
  - openpyxl
author: axoviq.com
license: AGPL-3.0-or-later
---

# XLSX Skill

Reads `.xlsx` files using `openpyxl` and `.csv` files using the stdlib `csv`
module, returning all rows as comma-separated text.

## Setup

```bash
pip install openpyxl
```

`.csv` files use only the Python standard library — no additional install required.

## Standalone usage

```python
import asyncio
from synthadoc.skills.xlsx.scripts.main import XlsxSkill

skill = XlsxSkill()

async def main():
    result = await skill.extract("/path/to/data.xlsx")
    print(result.text)      # all rows as comma-separated text
    print(result.metadata)  # {"rows": N, "sheets": N}  (xlsx only)

asyncio.run(main())
```

## When this skill is used

- Source path ends with `.xlsx` or `.csv`
- User intent contains: `spreadsheet`, `excel`, `csv`