Semantic Image Naming for Document-to-HTML Conversion for Openclaw

A professional utility that transforms generic document image exports into semantically named assets synchronized with their HTML references.

tinglan803-coder
v1.0.0
Apr 21, 2026
0
745
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install document-html-image-semantic-naming

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install document-html-image-semantic-naming using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Semantic Image Naming for Document-to-HTML Conversion?

This skill is a specialized solution for the doc, docx, and pdf to HTML conversion pipeline, focusing on transforming meaningless filenames like image1.jpg into reusable assets. By utilizing Openclaw Skills, it analyzes the intersection of document context—such as surrounding text, section headers, and captions—with the actual visual content of the image to generate intuitive filenames.

The core value lies in converting implicit document relationships into explicit, searchable, and human-readable metadata. This ensures that generated HTML files are not just functional, but also maintainable and optimized for long-term digital asset management.

Semantic Image Naming for Document-to-HTML Conversion Use Cases

  • Converting docx, ppt, or pdf files to HTML where images require meaningful semantic names.
  • Replacing generic media/image3.png filenames with context-aware titles.
  • Synchronizing image naming with document headers and section modules for better organization.
  • Preparing document-extracted assets for inclusion in larger digital libraries or SEO-driven web projects.

How Semantic Image Naming for Document-to-HTML Conversion Works

  1. Relationship Extraction: Maps every raw image to its HTML tag, surrounding paragraphs, and parent section headers.
  2. Role Identification: Classifies images into categories like cover, illustration, map, or atmospheric shot based on position.
  3. Semantic Refinement: Cross-references document text with visual content to ensure the filename accurately reflects the image.
  4. Batch Execution: Renames files, updates all HTML src attributes, and generates a traceability mapping file.
  5. Validation: Verifies that no broken links remain and that all semantic names follow the defined protocol.

Semantic Image Naming for Document-to-HTML Conversion Setup

To integrate this capability into your workflow with Openclaw Skills, follow these steps:

# Install the necessary conversion tools
pip install pandoc

# Add the semantic naming skill to your agent
openclaw install document-html-image-semantic-naming

# Run the naming process on your exported HTML directory
openclaw run document-html-image-semantic-naming --input ./dist --map ./mapping.csv

Semantic Image Naming for Document-to-HTML Conversion Data Schema & Taxonomy

The skill generates a mapping schema and organized directory structure as follows:

Attribute Type Description
source_name String The original generic filename (e.g., image4.jpeg)
context_info String Extracted text context or header reference
final_semantic_name String The new generated name following [Module]-[Scene]-[Orientation]-[Index]
mapping_log CSV/JSON A traceability file linking original files to their semantic versions

Semantic Image Naming for Document-to-HTML Conversion Advanced Features

  • Conflict resolution that prioritizes visual content when document context is too vague or generic.
  • Automatic orientation detection (landscape, portrait, or square) integrated directly into the naming convention.
  • Seamless integration with subsequent media preprocessing pipelines for image optimization.
  • Full support for complex HTML structures generated by Pandoc or PDF-to-HTML converters.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*