CommunityProductivity & Collaborationgithub.com

kkkkhazix/aihot

AI HOT (aihot.virxact.com) Chinese AI news query Skill. Fetches and summarizes the latest AI industry updates, model releases, and trending topics via a public REST API — no API keys or MCP server setup required.

What is aihot?

This skill is designed for AI agents (e.g., Claude Code, Cursor, Codex) to retrieve up-to-date Chinese AI news from AI HOT (aihot.virxact.com). It triggers on queries like "今天 AI 圈有什么" (What's up in AI today), "AI 日报" (AI daily report), "AI 热点" (AI hot topics), or even generic questions like "今天发生了什么" (What happened today) when the conversation context involves AI, LLMs, or startups. The skill executes a direct `curl` to the public REST API, fetches the latest data, and formats it into a Chinese markdown briefing. It requires zero configuration — no API keys, no MCP server — making it instantly usable. The key design principle is **do not undertrigger**: if the user asks for AI news and this skill is not invoked, the agent risks presenting outdated training data as current events, which is harmful to the user. The skill supports queries about daily news, featured items, papers, model releases, product launches, industry trends, and tips/opinions in the AI space.

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

Installed? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Ask in your favorite AI

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

Documentation

What does aihot do?

AI HOT (aihot.virxact.com) Chinese AI news query Skill. Use this when the user wants to know "What's up in AI today", "AI daily report", "AI HOT", "AI news", "AI hot topics", "Recent AI", "What have OpenAI/Anthropic/Google released recently", "AI hot today", "AI news today", "Show me AI industry trends", "What large models were released today", "AI circle yesterday", "View featured items", "AI HOT picks", "AI papers from the past week", "AI model releases", "AI product releases", "AI industry trends", "AI tips and insights", or any other Chinese AI news queries. Even if the user simply says "AI circle", "AI news", "AI daily", or just asks "What happened today" and the context is AI / large models / LLM / startup domain, this skill should be triggered. The skill directly curls a public REST API to fetch data and compiles it into a Chinese markdown briefing — no API keys or MCP server configuration needed. Do not undertrigger — if the user asks for AI news and you don't invoke this skill, you are serving stale training data as today's news, which is harmful to the user.

Individual skills in this repo

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

kkkkhazix/hv-analysis

横纵分析法(Horizontal-Vertical Analysis)深度研究Skill。由数字生命卡兹克提出,融合了索绪尔的历时-共时分析、社会科学的纵向-横截面研究设计、商学院案例研究法与竞争战略分析的核心思想。 当用户想要系统性研究一个产品、公司、概念、技术或人物时使用。核心是双轴分析:纵轴追踪从诞生到当下的完整生命历程(以叙事故事呈现),横轴在当下时间截面上与竞品/同类进行系统性横向对比,最后交叉两条轴产出独到洞察。最终产出一份排版精美的PDF研究报告。 触发词包括但不限于:横纵分析、研究一下、帮我分析、深度研究、做个研究、调研一下、竞品分析、帮我看看这个东西怎么样、这个产品/公司/概念是怎么回事、帮我摸清楚、帮我搞懂、帮我做个deep research。 即使用户只是说"帮我了解一下XX"或"XX是什么来头",只要上下文暗示需要系统性的深度研究(而非简单的概念解释),都应该触发。也适用于用户丢来一个产品名、公司名、技术名词说"帮我研究一下这个"的场景。 不要用于简单的名词解释(用户只是问"XX是什么")、不要用于公众号写作(那个用khazix-writer)、不要用于纯标题摘要生成(用wechat-title)。

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