CommunityResearch & Data Analysisgithub.com

kkkkhazix/hv-analysis

Horizontal-Vertical Analysis: A deep research Skill for systematically analyzing products, companies, concepts, technologies, or individuals. Proposed by Kazik Digital Life, it integrates Saussure's diachronic-synchronic analysis, social science longitudinal-cross-sectional research designs, business school case study methods, and competitive strategy analysis.

What is hv-analysis?

This skill, named hv-analysis, is designed for AI agents like Claude Code, Cursor, or Codex to perform deep, structured research on a given subject (e.g., a product, company, concept, technology, or person). It proposes a dual-axis framework: the vertical axis traces the subject's complete lifecycle from inception to present as a narrative story; the horizontal axis performs systematic cross-sectional comparisons with competitors or peers at the current time slice. By crossing these two axes, the agent generates unique insights and outputs a beautifully formatted PDF research report. The skill is triggered by specific keywords and phrases like '横纵分析', '帮我研究一下', or '深度研究', and should not be used for simple definitions or casual writing tasks.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/kkkkhazix/khazix-skills/tree/main/skills/hv-analysis

Installed? Explore more Research & Data Analysis skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does hv-analysis do?

Horizontal-Vertical Analysis (H-V Analysis) Deep Research Skill. Proposed by Kazik Digital Life, it integrates Saussure's diachronic-synchronic analysis, longitudinal-cross-sectional research designs from social sciences, business school case study methods, and competitive strategy analysis. Use this when the user wants to systematically research a product, company, concept, technology, or individual. The core is dual-axis analysis: the vertical axis traces the complete life journey from inception to the present (presented as a narrative story), while the horizontal axis provides a systematic cross-sectional comparison with competitors/peers at the current time slice. Finally, cross the two axes to produce unique insights. The final output is a beautifully formatted PDF research report. Trigger words include but are not limited to: horizontal-vertical analysis, research, help me analyze, deep research, do a study, investigate, competitive analysis, tell me what this is about, what is this product/company/concept, help me figure it out, help me understand, do a deep research. Even if the user just says 'help me understand XX' or 'what's the story behind XX', as long as the context implies a need for systematic deep research (rather than a simple definition), the skill should be triggered. It is also suitable for scenarios where the user throws out a product name, company name, or technical term and says 'research this for me'. Do not use for simple definitions (user just asks 'what is XX'), do not use for WeChat public account writing (use khazix-writer for that), do not use for pure title/summary generation (use wechat-title).

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

kkkkhazix/aihot

AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI news today"、"看一下 AI 行业动态"、"今天有什么大模型发布"、"昨天 AI 圈"、"看下精选条目"、"AI HOT 精选"、"最近一周的 AI 论文"、"AI 模型发布"、"AI 产品发布"、"AI 行业动态"、"AI 技巧与观点" 等任何中文 AI 资讯查询时使用。即使用户只说"AI 圈"、"AI 新闻"、"AI 日报",或者只是问"今天发生了什么"且上下文是 AI / 大模型 / LLM / 创业领域,也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报,不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻,对用户有害。

kkkkhazix/khazix-writer

数字生命卡兹克(Khazix)的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于:写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下",只要上下文涉及内容创作和公众号输出,都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容(小红书帖子、推特、朋友圈)或纯标题摘要生成(那个用wechat-title skill)。

kkkkhazix/neat-freak

End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.

Related Skills