← Back to Skills Marketplace
290
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install docx-to-html
Description
Use this skill whenever the user has a DOCX file (.docx) and wants to convert, read, view, extract content from, or process it in any way — including summari...
README (SKILL.md)
DOCX to HTML Converter
This skill provides a straightforward method to convert Microsoft Word (.docx) documents into clean, semantic HTML, making them suitable for various web-based and AI-driven applications.
Compatibility
- Python 3 (for the conversion wrapper)
- Node.js with
mammothinstalled (core conversion engine)
To install Node.js dependencies, run once from the scripts/ directory:
npm install
Use Cases
- Browser-Based Viewing: Convert DOCX documents for display in web browsers without requiring Microsoft Word.
- AI-Ready Content: Prepare DOCX content for LLMs for tasks like summarization, Q&A, and semantic search.
- Web Integration: Integrate Word document content into web applications, CMS, or online editors.
- Data Extraction: Extract structured data (tables, lists, headings) from DOCX files for automated reporting and analysis.
- Search and Indexing: Enable full-text and vector search by converting DOCX content into easily indexable HTML.
Workflow
-
Locate DOCX File: Identify the path to the
.docxfile to convert. -
Run Conversion Script: Execute the Python wrapper from the skill's
scripts/directory:python3 \x3Cskill-dir>/scripts/convert.py \x3Cinput_path.docx> \x3Coutput_path.html>Replace
\x3Cskill-dir>with the actual path where this skill is installed. -
Verify Output: Open the generated
.htmlfile in a browser and check:- Headings (
\x3Ch1>,\x3Ch2>, etc.) appear at the correct hierarchy levels - Tables render with the expected rows and columns
- Lists appear as bullet or numbered items (not plain text)
- Bold, italic, and inline formatting are preserved
- Images are visible (embedded as base64 by default)
- Headings (
-
Process HTML: Use the resulting HTML for further tasks like summarization, indexing, or display.
Bundled Resources
scripts/docx-converter.js: Core Node.js conversion logic usingmammoth.js.scripts/convert.py: Python wrapper for invoking the Node.js converter.scripts/package.json: Node.js dependency manifest (includesmammoth).
Technical Details
The conversion leverages mammoth.js, which prioritizes semantic meaning over visual replication:
- Semantic Conversion: Document structure maps to proper HTML — headings become
\x3Ch1>/\x3Ch2>, lists become\x3Cul>/\x3Col>, etc. - Basic Styling: Bold, italics, and common paragraph styles are preserved.
- Image Embedding: Images are extracted and embedded as base64 data URIs in the HTML output.
Troubleshooting
| Problem | Likely Cause | Fix |
|---|---|---|
node: command not found |
Node.js not installed | Install Node.js (v16+) |
Cannot find module 'mammoth' |
npm deps missing | Run npm install in scripts/ |
| Empty or garbled output | Corrupted or password-protected DOCX | Try re-saving the file from Microsoft Word |
| Missing images | Large embedded images | Check mammoth.js image size limits in docx-converter.js |
Limitations
- Advanced or highly specific styling from the original DOCX may not be perfectly replicated in the HTML output.
- Features like tracked changes, comments, or complex layout elements may be simplified or omitted.
Usage Guidance
This skill's implementation (Python wrapper + Node/mammoth) is coherent with its stated purpose, but the registry metadata omits required binaries (Node.js and Python) — treat that as a packaging oversight. Before installing or running: (1) inspect package-lock.json for unfamiliar packages (already provided here; mammoth and common deps look normal); (2) run npm install in a sandbox or isolated environment, not on a production host; (3) ensure Node.js (v16+) and Python 3 are available; (4) if you will process sensitive documents, run the conversion in a secure/local environment since the code writes files to disk and npm packages will be downloaded; and (5) if you need a higher assurance, ask the publisher for corrected metadata and a signed release or a packaged install spec.
Capability Analysis
Type: OpenClaw Skill
Name: docx-to-html
Version: 1.0.0
The OpenClaw AgentSkills bundle 'docx-to-html' is classified as benign. The skill's purpose is to convert DOCX files to HTML, which is a legitimate utility function. The `SKILL.md` provides clear instructions for the AI agent to use the skill for DOCX processing without any evidence of prompt injection aiming for malicious objectives. The core conversion logic in `scripts/convert.py` and `scripts/docx-converter.js` uses `subprocess.run` with a list of arguments, effectively mitigating shell injection risks from user-provided file paths. Dependencies listed in `scripts/package.json` and `scripts/package-lock.json` are standard for the `mammoth` library, which is a well-known DOCX parsing tool, and do not indicate any malicious intent or suspicious supply chain issues.
Capability Assessment
Purpose & Capability
The code and SKILL.md match the stated purpose (using mammoth.js to convert .docx to HTML). However the registry metadata declares no required binaries or env vars while the SKILL.md explicitly requires Python 3 and Node.js; that mismatch is unexpected and should be corrected.
Instruction Scope
Runtime instructions are narrowly scoped to locating a .docx file, running the provided convert.py wrapper (which calls the included Node script), and verifying the HTML output. The instructions do not request or reference unrelated system files, credentials, or external endpoints.
Install Mechanism
There is no formal install spec in the registry; instead the SKILL.md instructs running 'npm install' in scripts/. That downloads packages from the public npm registry (package-lock.json is provided). This is a common pattern but increases risk compared with an explicit reviewed install spec; the lockfile points to known packages (mammoth and dependencies) and there are no download-from-arbitrary-URL steps.
Credentials
The skill does not request environment variables or credentials and the code does not access secrets or unrelated config paths. All file I/O is limited to the user-supplied input .docx and the specified output .html.
Persistence & Privilege
The skill is not 'always' enabled and does not attempt to modify other skills or global agent settings. It runs on-demand and does not request elevated or persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install docx-to-html - After installation, invoke the skill by name or use
/docx-to-html - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of docx-to-html skill.
- Converts DOCX documents to clean, semantic HTML using mammoth.js.
- Includes both a Node.js converter script and a Python wrapper for easy integration.
- Supports extracting headings, tables, lists, inline formatting, and images from DOCX files.
- Enables use-cases like browser viewing, content extraction for AI, and web integration.
- Includes troubleshooting guidance and outlines current limitations.
Metadata
Frequently Asked Questions
What is DOCX TO HTML CONVERTER?
Use this skill whenever the user has a DOCX file (.docx) and wants to convert, read, view, extract content from, or process it in any way — including summari... It is an AI Agent Skill for Claude Code / OpenClaw, with 290 downloads so far.
How do I install DOCX TO HTML CONVERTER?
Run "/install docx-to-html" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is DOCX TO HTML CONVERTER free?
Yes, DOCX TO HTML CONVERTER is completely free (open-source). You can download, install and use it at no cost.
Which platforms does DOCX TO HTML CONVERTER support?
DOCX TO HTML CONVERTER is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created DOCX TO HTML CONVERTER?
It is built and maintained by Bibek KC (@bibekyess); the current version is v1.0.0.
More Skills