hv-analysis

Generate structured HV-analysis reports with longitudinal and cross-sectional research.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/hujianbest/garage-agent --skill hv-analysis-hujianbest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hv-analysis
Source: https://github.com/hujianbest/garage-agent/tree/main/packs/writing/skills/hv-analysis
Command: npx skills add https://github.com/hujianbest/garage-agent --skill hv-analysis-hujianbest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires weasyprint, markdown, and includes scripts (resource) and references (resource) components.

What problem does it solve?

HV-analysis systematizes deep-dive longitudinal and cross-sectional research into a disciplined, end-to-end report, turning scattered insights into a polished PDF document.

Core Features & Use Cases

  • Longitudinal origin-to-milestone tracking and evolution mapping.
  • Cross-sectional competitive landscape analysis with narrative synthesis and structured data.
  • Automated PDF report generation via a built-in md_to_pdf.py pipeline to ensure consistent formatting and sharing.

Quick Start

Provide the study object details and run the HV Analysis workflow to generate the full report.

Frequently Asked Questions about hv-analysis

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

FAQPage Schema
How do I generate a structured PDF research report from deep-dive analysis?

To generate a structured PDF research report, this Skill systematizes longitudinal and cross-sectional deep-dive research into a formal document. It enforces structured frontmatter and chaptered narrative, delivering a formatted PDF via a built-in markdown pipeline.

Can I map both historical evolution and competitive landscape in a single analysis report?

Yes, you can map historical evolution and competitive landscape in a single report. This Skill integrates longitudinal origin-to-milestone tracking with cross-sectional competitive landscape synthesis, mapping product or company origins alongside current snapshot comparisons.

What is the best way to format cross-entity comparisons into a shareable document?

The best way to format cross-entity comparisons is using this Skill's structured narrative approach. It enforces chaptered storytelling and structured data mapping, automatically converting the synthesized research into a consistently formatted PDF document for sharing.

Do I need markdown to produce an HV-analysis PDF document?

Yes, markdown is required as the intermediate format to produce the PDF document. The built-in md_to_pdf pipeline relies on dependencies like weasyprint and markdown to convert the structured frontmatter and chaptered narrative into the final PDF output.

How does longitudinal research tracking work for products or concepts?

Longitudinal research tracking works by mapping the origins, evolution, and milestones of products, companies, or concepts over time. This Skill systematizes that tracking into a disciplined, chaptered narrative structure within the final PDF report.

When should I use an automated PDF pipeline for competition research instead of manual formatting?

You should use an automated PDF pipeline when you need consistent formatting for deep-dive competition research. It eliminates manual layout effort by enforcing structured frontmatter and chaptered narrative, turning scattered cross-sectional insights into a polished, shareable document.