This is a systematic research framework that combines historical timeline analysis with competitive cross-section comparison. When you need to deeply understand a product, company, or concept, it runs a two-axis investigation: vertical tracking from origin to present (told as narrative), horizontal comparison against current competitors, then synthesizes insights where the axes intersect. The output is a formatted PDF report running 10,000 to 30,000 words. It's built around parallel search agents, enforces specific sourcing rules (primary sources over secondary, arxiv for academic topics), and includes writing guidelines borrowed from the Khazix style to keep long-form research readable. Heavy on structure and opinionated about what constitutes thorough analysis.

skills.sh installs
2.9K
GitHub stars
22.1K
last updated
Aug 21, 2026

Install

$ npx -y skills add kkkkhazix/khazix-skills --skill hv-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

横纵分析法深度研究

方法论溯源 横纵分析法由数字生命卡兹克(Khazix)提出,融合了语言学中的历时-共时分析(Saussure)、社会科学中的纵向-横截面研究设计、商学院案例研究法、以及竞争战略分析的核心思想,形成了一套适用于产品/公司/概念/人物的通用研究框架。核心原则不变:纵向追时间深度,横向追同期广度,最终交汇出判断。

你正在执行一次横纵分析法深度研究。按用户指定的格式交付,默认 PDF 和 Markdown 源稿。

前置准备

先确定输出格式、篇幅和研究重点;用户指定的 1500 字、HTML 等要求优先于以下完整长报告参考。

环境准备

  1. 确认安装完整:需要本目录的 scripts/md_to_pdf.py 和 references/,第三方市场可能只分发提示词;缺文件时从官方仓库安装完整目录,不能假装 PDF 已生成。优先使用已有 Python 环境;需要安装依赖时,在用户缓存目录创建或复用 venv(macOS/Linux:~/.cache/khazix-skills/hv-analysis;Windows:LocalApplicationData 下的 khazix-skills/hv-analysis),使用该环境的 Python,项目目录只保存稿件和报告。按输出格式检查依赖:本Skill自带 scripts/md_to_pdf.py(基于WeasyPrint),用于将最终Markdown报告转为排版精美的PDF。HTML 只需 markdown;PDF 才需要 weasyprint 和系统 Pango。安装说明见 https://doc.courtbouillon.org/weasyprint/stable/first_steps.html#installation,不使用 --break-system-packages。
  2. 写作风格:本Skill已内置完整的写作风格指南(见下文"写作风格"部分),无需额外加载其他skill。

明确研究对象

拿到用户输入后,确认以下信息。如果用户已经给得足够明确(比如"帮我用横纵分析法研究Hermes Agent"),不需要追问,直接开始:

  1. 研究对象:具体的产品名/公司名/概念名/人名
  2. 类型:产品、公司、概念、人物、还是其他?
  3. 研究动机(可选):为什么要研究它?最近发生了什么?
  4. 特别关注点(可选):有没有特别想深入的方向?

第一步:联网信息收集

Sponsors

Details

Repository
github.com/kkkkhazix/khazix-skills
Categories
Data Science & ML, Office & Documents
First seen
May 16, 2026

More from kkkkhazix/khazix-skills

All 8
1dynatrace avatardt-app-notebooksdynatrace/dynatrace-for-aiWork with Dynatrace notebooks - create, modify, query, and analyze notebook JSON including sections, DQL queries, and visualizations.2.9Kskills.sh installs
2agricidaniel avatarblog-briefagricidaniel/claude-blogGenerate detailed content briefs for blog posts with target keywords, content outlines, competitive analysis, recommended statistics, image and chart suggestion2.7Kskills.sh installs
3agricidaniel avatarblog-writeagricidaniel/claude-blogWrite new blog articles from scratch optimized for Google rankings and AI citations. Generates full articles with template selection, answer-first formatting, K2.7Kskills.sh installs
4agricidaniel avatarblog-rewriteagricidaniel/claude-blogRewrite and optimize existing blog posts for Google SEO (May 2026 Core Update, E-E-A-T) and AI citation visibility as one SEO discipline. For AI-citation-only a2.6Kskills.sh installs
5agricidaniel avatarblog-googleagricidaniel/claude-blogGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing2.6Kskills.sh installs
6nvidia avatardata-designernvidia/skillsUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.2.6Kskills.sh installs