Setup & Installation
openclaw skills install @lkyyyy320/office-to-md-v2
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install office-to-md-v2
What This Skill Does
Converts PDF, DOC, DOCX, and PPTX files to Markdown format within OpenClaw. Uses pdf-parse, mammoth, word-extractor, and python-pptx under the hood. Legacy .doc files are supported including Chinese-encoded content.
Handles legacy .doc binary format and Chinese encoding where most converters require .docx or clean UTF-8 input.
When to use it
- Extract text from a legacy .doc contract for analysis
- Convert a PDF report to Markdown for LLM processing
- Batch-convert a folder of mixed office documents
- Pull slide text from a PPTX presentation
- Read a DOCX with preserved heading structure
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert report.doc to Markdown and show a word count
AGENT
- 1Validate the file path exists using read()
- 2Check the file extension is in the supported list
- 3Run the skill via exec: node openclaw-skill.js report.doc
- 4Read the output report.md from disk
- 5Count words and lines, return a preview of the content
OUTPUT
report.md created; word count, line count, and a 200-character preview returned to the user