hads

Add semantic markers and AI-visible annotations to Markdown documents.

1|1|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/gaoqiongxie/skills-ai --skill hads-gaoqiongxie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hads
Source: https://github.com/gaoqiongxie/skills-ai/tree/main/hads
Command: npx skills add https://github.com/gaoqiongxie/skills-ai --skill hads-gaoqiongxie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Traditional Markdown documents are optimized for human readability but often poorly parsed by AI models, leading to missed context, misinterpreted key decisions, and incorrect extraction of structured data from technical documentation.

Core Features & Use Cases

  • Semantic Heading Markers: Label document sections with tags like [CONTEXT], [DECISION], and [RATIONALE] so AI can instantly identify content types without reading full paragraphs.
  • AI-Visible Annotation Blocks: Add context-rich notes for AI to highlight critical warnings, cross-references, and background information without disrupting human reading flow.
  • Structured Data Annotations: Tag table columns with explicit data types for accurate AI parsing, plus lightweight ADR templates to standardize architecture decision records.
  • Use Case: A development team can use HADS to format their API design documents so both new engineers and AI coding assistants can quickly locate authentication requirements, decision rationales, and pending tasks without confusion.

Quick Start

Use the hads skill to convert your existing product requirement document into HADS format with semantic headings and AI annotation blocks.

Frequently Asked Questions about hads

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

FAQPage Schema
How do I make Markdown technical documentation readable for both humans and AI?

Make Markdown technical documentation AI-friendly by applying lightweight semantic markers like [CONTEXT] and [DECISION], AI-visible annotation blocks, and structured data tags for accurate dual parsing.

Why does my AI coding assistant misinterpret key decisions in my Markdown API specifications?

AI misinterprets API specifications because traditional Markdown lacks semantic structure. Adding AI-visible annotation blocks and structured data type labels clarifies critical warnings and decision rationales for accurate AI parsing.

What is the best way to format architecture decision records for AI parsing?

The best way to format architecture decision records for AI parsing is using lightweight ADR templates with semantic heading markers to instantly identify content types without reading full paragraphs.

Can I tag table columns with explicit data types in Markdown for accurate AI extraction?

Yes, you can tag table columns with explicit data types in Markdown. Using structured data annotations allows AI systems to accurately extract and parse tabular data without confusion.

Does adding semantic markup to product requirement documents disrupt human reading flow?

Adding semantic markup to product requirement documents does not disrupt human reading flow. The markers, annotation blocks, and data labels are lightweight and maintain natural readability while enabling AI context extraction.

How to convert existing technical documentation into an AI-friendly format?

Convert existing technical documentation into an AI-friendly format by integrating semantic heading markers, adding AI-visible annotation blocks for context, and tagging structured data for dual parsing.