What if the required tool isn't installed?

The skill uses which to verify installation and will inform you that the dependency is missing so you can install it before retrying.

Can I convert multiple files at once?

Yes. Use shell loops or glob patterns to batch process files, but ensure output names are unique to avoid overwriting.

How do I know the conversion succeeded?

A post-run check confirms the output file exists and contains data; if not, review error messages from the Bash command.

file-converter

npx machina-cli add skill next-open-ai/openclawx/file-converter --openclaw

Files (1)

SKILL.md

980 B

File Converter Skill

Use this skill to convert a file from one format to another or extract content from files.

Workflow

Identify the source file format and the target format.
Determine which system tool is available and best suited for the conversion:
- For document conversion (Markdown, HTML, Word): pandoc
- For images (resize, format change): convert or magick (ImageMagick)
- For PDF text extraction: pdftotext
- For OCR on images: tesseract
Use the bash tool to check if the required tool is installed (e.g., which pandoc). If not, inform the user they need to install the dependency.
Execute the conversion command via bash.
Verify the output file exists and has content, then notify the user.

Source

git clone https://github.com/next-open-ai/openclawx/blob/main/presets/workspaces/file-assistant/skills/file-converter/SKILL.md

View on GitHub

Overview

File-converter enables format transformation and content extraction using common Bash tools. It supports pandoc for document conversions, ImageMagick for image tasks, and pdftotext or tesseract for PDF text and OCR. The workflow validates tool availability before executing conversions to ensure reliable results.

How This Skill Works

The skill identifies the source and target formats, selects the appropriate tool (pandoc for documents, convert/magick for images, pdftotext for PDF text, or tesseract for OCR), and uses which to verify installation. It then runs the conversion command in Bash and finally checks that the output file exists and contains content.

When to Use It

Convert Markdown, HTML, or Word documents to other formats using pandoc
Convert DOCX to PDF or HTML to Markdown via pandoc
Resize, reformat, or convert images with ImageMagick (convert/magick)
Extract text from a PDF using pdftotext
Perform OCR on an image or screenshot with tesseract to produce searchable text

Quick Start

Step 1: Identify the source format and the desired target format
Step 2: Check installation with which pandoc / convert / pdftotext / tesseract as appropriate
Step 3: Run the conversion command in Bash and verify the output file exists and has content

Best Practices

Check tool availability with which before attempting a conversion
Test conversions on small samples to verify formatting and output quality
Verify the output file exists and contains content after the command runs
Handle unsupported format pairs gracefully with a clear error message
Document the exact command used and output file path for reproducibility

Example Use Cases

Convert a Markdown file to HTML using pandoc
Transform a DOCX into PDF with pandoc
Resize a JPEG and save as PNG using ImageMagick
Extract text from a PDF with pdftotext
Run OCR on a PNG image with tesseract to produce a TXT file

Frequently Asked Questions

Add this skill to your agents