Skip to content
SkillMixed6,516 tokens in use

HV Analysis

Deep research on a product, company, concept or person: a vertical history, a horizontal competitor map and a verdict where they cross, as a sourced PDF.

22,429 stars on the repository MIT LicenseKKKKhazix/khazix-skills · hv-analysis
/plugin marketplace add KKKKhazix/khazix-skills /plugin install khazix-skills@khazix-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing HV Analysis costs

409tokens idle
6,516tokens in use
9,397tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/md_to_pdf.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter4/15
  • Structure16/25
  • Examples9/15
  • Output5/15
  • Size9/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 192
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 192
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/md_to_pdf.py, line 303

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance84
  • Community60
  • Maturity28
  • Momentum40

HV Analysis, the horizontal-vertical method, researches a subject along two lines. The vertical line tells its story from origin to today with causes for each turn. The horizontal line compares it with current competitors or peers, using real user voices.

The two lines then cross in a section that explains how history shaped today’s position and sets out three scenarios. The default delivery is a report of ten to thirty thousand characters as PDF plus a Markdown source, with every key fact numbered against a source list.

What You Get

  • A long-form report with a one-line definition, vertical analysis, horizontal analysis and a crossing section
  • Numbered citations that tie each key fact to a source list marked first-hand, second-hand or the party’s own claim
  • A PDF with cover, headers and Chinese fonts, plus the Markdown source
  • Flags in the text for single-source facts, conflicting accounts and missing information

Common Use Cases

  • Researching a competitor or a whole competitive field before a decision
  • Preparing source material before writing an article
  • Learning a new technology concept or company history from scratch
  • Profiling a person’s career against peers in the same field

What Makes It Unique

The method forces a verdict from the crossing of two views, so a timeline and a comparison table alone do not count as finished. The evidence rules are strict: current facts need current sources, a ledger records each fact’s source, event date and publication date, the agent searches for evidence against its own emerging judgement, and it states gaps and never fills them from memory. It is also explicit that it will not claim a PDF exists when the converter could not run.

Under The Hood

The agent searches the web and reads pages with whatever search and fetch tools the host provides, optionally splitting the three research lines across subagents, and it may query the arXiv API for papers. It writes the report as Markdown in your working folder. To make a PDF it runs a bundled Python script through the shell; for that it creates or reuses a virtual environment in your user cache folder, installs the markdown and weasyprint packages with pip, and writes HTML and PDF files. It can also save the Markdown into an Obsidian vault path you name.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers