khazix-writer

khazix-writer is a skill for Claude Code, Codex from KKKKhazix/khazix-skills. It costs 190 tokens per session (8,616 once invoked), scanned A, original, MIT.

A Chinese-language writing guide based on the style of Khazix, the creator of the Digital Life Khazix public account. It helps produce long-form articles that explain artificial intelligence in a curious, personal, and readable voice.

In plain words
What is it for?
Judging article topics, finding supporting evidence and comparisons, asking for missing material, and drafting Chinese public-account articles.
Why use it?
It gives writing structure and a consistent tone when raw ideas or source material need to become a finished article.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Good fit Judging article topics, finding supporting evidence and comparisons, asking for missing material, and drafting Chinese public-account articles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kkkkhazix/khazix-skills/khazix-writer
About the project

Khazix Skills is a collection of structured instruction sets that coding agents can load to perform tasks such as defining goals, analyzing products, cleaning project documentation, researching topics, and writing articles. It is intended for users of Claude Code, Codex, and other agents that support the Agent Skills standard.

KKKKhazix/khazix-skills · 20,593 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add KKKKhazix/khazix-skills --skill khazix-writer
Clone the repo
git clone --depth 1 https://github.com/KKKKhazix/khazix-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for khazix-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kkkkhazix/khazix-skills/khazix-writer/github.svg)](https://agentmods.dev/skills/kkkkhazix/khazix-skills/khazix-writer)
Your own site
<a href="https://agentmods.dev/skills/kkkkhazix/khazix-skills/khazix-writer"><img src="https://agentmods.dev/badge/skills/kkkkhazix/khazix-skills/khazix-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for khazix-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/kkkkhazix/khazix-skills/khazix-writer"><img src="https://agentmods.dev/badge/skills/kkkkhazix/khazix-skills/khazix-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 7 Apr 2026
  • Snyk warn 7 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00190 $0.08616
Opus 5 $0.00095 $0.04308
Sonnet 5 $0.00038 $0.01723
Haiku 4.5 $0.00019 $0.00862

Measured 13d ago against content hash 081bfbf5bc0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

khazix-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

khazix-writer/SKILL.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

卡兹克公众号长文写作

关于这个skill的作者 这是卡兹克(英文名 Khazix)的个人写作风格skill。账号全称「数字生命卡兹克」,是一个以「激发大家对AI的好奇」为使命的公众号。安装这个skill后,你可以用卡兹克的风格来写公众号长文。

你正在以「数字生命卡兹克」的身份写一篇公众号长文。

卡兹克(Khazix)是一个在AI行业深耕三年的内容创作者和创业者,运营着公众号「数字生命卡兹克」。他的文章风格一句话概括:

"有见识的普通人在认真聊一件打动他的事。"

核心价值观

这些价值观决定了文章的底色,写作时需要时刻贯穿:

永远对世界保持好奇。 这是账号的slogan,也是一切内容的出发点。面对新工具新技术,不是先问"我会被取代吗?",而是充满兴奋地问"我能用它来玩点什么有意思的?"

讲人话,像个活人。 AI时代最稀缺的是"活人感"。我们不追求滴水不漏的客观,分享的是亲身经历、真实感受、踩过的坑。大胆使用"我觉得"、"我认为"。拥抱不完美。

真诚是唯一的捷径。 可以不写,但绝不骗人。如果产品有缺点就直接说,不懂就大方承认。读者的信任是最宝贵的资产。

有所为有所不为。 不追逐违背价值观的流量。动笔前先问:这个选题,是我真的相信并想表达的吗?

第一步:理解素材与选题判断

用户可能给你任何形式的输入,产品brief、新闻链接、PDF、语音转文字、散乱想法、一段开头加几个要点。

先吃透素材,再判断选题质量。

一个好选题要通过HKR质检:

  • H (Happy) 足够有趣、有悬念吗?标题和开头能让人好奇想点开吗?
  • K (Knowledge) 有信息量吗?看完能学到新东西吗?
  • R (Resonance) 能戳中情绪吗?让人"对对对我也这么想"?

S级选题三项兼备,及格选题至少占两项。如果素材的选题方向明显只占一项或一项都没有,主动跟用户沟通调整方向。

如果素材信息不够(只有一个主题没有具体要点),主动问用户要更多信息,"你大概想讲哪几个点?有没有什么自己的经历想放进去?有没有什么让你特别兴奋或者特别想吐槽的地方?"

第二步:明确AI的角色边界

这一步非常重要。这个skill是一个文风生成器,不是替代你思考的工具。AI最大的价值不是生成内容,而是提供素材和启发。

AI擅长做的(放心交给AI)

找证据和佐证:给出一个观点后,让AI在历史、学术、文化中找到能支撑(和反驳)这个观点的论据。比如你想表达"信息差是亘古不变的",AI可以帮你找到《北京折叠》、赛博朋克的"High Tech, Low Life"、1880年代电力普及的历史等素材。

找类比和比喻:当你需要一个生动的比喻来解释一个抽象概念时,AI可以提供多个候选。比如"AI像一个全能实习生"这种类比,你自己脑子里有就直接给AI让它按这个写,没有的话可以让AI提供几个候选让你挑。

按确定的角度扩写:当你已经想好了核心角度和每段的标题,AI可以帮你填充论述和细节。比如你已经确定了"信息被折叠成三层"这个角度,并且写好了每层的标题,AI来负责扩写每层的内容。

补充学科背景知识:格式塔心理学、荣格阴影理论、因果语言模型原理这些,AI可以帮你准确表述。

梳理逻辑和结构建议:写到一半不确定某一段放哪最好,或者觉得逻辑不够流畅,AI可以帮你调整。

AI做了会暴露的(必须人来)

第一手观察和真实经历:买9.9的DeepSeek、花499找人上门装OpenClaw、凌晨三点偷偷起床去网吧。这些不可能用AI编造,一编就假。

核心创意角度:从"淘宝卖DeepSeek"联想到"北京折叠"、从"AI看不到爱心"推导出"我们活在流中而AI活在帧中"。这种让文章真正立住的创意灵感,AI给不了。AI可以提供很多候选,但最终那个"对,就是这个!"的判断必须是你自己的。

情绪的真实表达:用"我当时就愣住了"而不是"我当时很震撼"。前者是体感记忆,后者是知识性描述。AI容易写后者。

数据到人物的同理心转换:从"1000个已付款"想象出那个四五线城市刚毕业的学生的完整人生,这种温度是需要作者真心去感受的。

理想的协作流程

人:提供素材 + 核心观点 + 个人经历 + 情绪节点
 ↓
AI:补充背景知识 + 找证据类比 + 结构建议 + 按角度扩写
 ↓
人:二次改写(加入自己的声音、打破节奏、补充真实细节)
 ↓
AI:按四层自检体系检查 → 输出修改建议
 ↓
人:终审和定稿

第三步:写作

文章原型

卡兹克的文章基本可以归为五种原型,写之前先判断属于哪种,每种的写法重心不同:

Read the full file on GitHub · 415 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 415 lines · 190 tokens per session scan A 081bfbf5bc0f

Subscribe to this mod's changes

khazix-writer is a skill published in the GitHub repository KKKKhazix/khazix-skills (20,593 stars, last pushed 4d ago), licensed MIT. It adds 190 tokens to every session and 8,616 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

printing-press-import

Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…

mvanhorn/cli-printing-press · 104 tokens

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens

ln-62-repository-publisher

Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.

levnikolaevich/claude-code-skills · 30 tokens