skills.rest
jasonhnd
jasonhndCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

make-doc-skill

Generate self-contained HTML documents from URLs, PDFs, or text.

1|Updated Apr 11, 2026
Search Tags:#workflow#HTML#document-generation#make-doc-skill#visual-document#brain-router-canvas
One-click install
npx skills add https://github.com/jasonhnd/makedocskill --skill make-doc-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: make-doc-skill
Source: https://github.com/jasonhnd/makedocskill/tree/main
Command: npx skills add https://github.com/jasonhnd/makedocskill --skill make-doc-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill converts dense, complex information into beautifully designed, self-contained HTML documents, dramatically reducing the time and effort needed to produce publication-ready visuals from varied sources.

Core Features & Use Cases

  • Self-contained HTML output for a single-page scroll or 16:9 slides, compatible with knowledge bases and print formats
  • Quick Mode: one-shot HTML generation from a YouTube URL, web URL, PDF, or raw text
  • Full Mode: an 8-step pipeline (CI extraction, pre-interview, material organization, sparring, composition, review, and HTML generation) that enforces CI and design fidelity
  • Multilingual support (ja/zh/en) for cross-language collaboration and distribution
  • Strict adherence to design rules and CI guidelines, enabling consistent brand storytelling

Quick Start

Provide the material you want transformed and instruct the AI to produce a self-contained HTML document.

Frequently Asked Questions about make-doc-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a PDF or web URL into a self-contained HTML document?▼

To convert a PDF or web URL into a self-contained HTML document, use Quick Mode for one-shot generation. Provide the source link, and the workflow will extract the content to produce a standalone HTML file.

What is the best way to generate multilingual visual documents from raw text?▼

The best way to generate multilingual visual documents from raw text is via a structured three-layer workflow. It processes raw text into standalone HTML files while supporting Japanese, Chinese, and English outputs.

How does the Full Mode pipeline work for complex HTML document generation?▼

Full Mode works for complex HTML document generation by running an 8-step pipeline. It extracts content, organizes materials, and executes composition and review steps to enforce design fidelity before generating the final HTML.

Can I create 16:9 slide presentations directly from a YouTube URL?▼

Yes, you can create 16:9 slide presentations directly from a YouTube URL. The generator's Quick Mode accepts YouTube URLs as input to produce single-page scroll or 16:9 slide HTML formats.

Does this visual document generator support strict brand CI guidelines?▼

Yes, the visual document generator supports strict brand CI guidelines. The Full Mode pipeline explicitly enforces CI extraction and design rules to ensure consistent brand storytelling in the final HTML output.

Related Skills

Explore More Content & Communication Skills→
Miosa-osaMiosa-osa
226

reduce

Extract atomic claims with provenance and confidence from source materials.

Official
Intermediate
allen-hsuallen-hsu
1

creating-info-cards

Generate self-contained HTML info cards with embedded CSS and fonts.

Community
Advanced
whichguywhichguy

popular-web-designs

Provide HTML/CSS templates for popular brand design systems.

Community
Basic
zephyrwang6zephyrwang6
333

web-scraper

Fetch web page content and convert HTML to clean Markdown.

Community
Intermediate