Human Writing is a writing and revision skill that guides AI to produce Chinese prose with a distinct, human-like voice. It is for creating or editing articles, stories, posts, scripts, explanations, reviews, and other Chinese writing. The catalogue entry contains the skill used by coding agents.
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.
npx skills add KKKKhazix/human-writing --skill human-writinggit clone --depth 1 https://github.com/KKKKhazix/human-writingWrote 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.
[](https://agentmods.dev/skills/kkkkhazix/human-writing/human-writing)<a href="https://agentmods.dev/skills/kkkkhazix/human-writing/human-writing"><img src="https://agentmods.dev/badge/skills/kkkkhazix/human-writing/human-writing/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.
<a href="https://agentmods.dev/skills/kkkkhazix/human-writing/human-writing"><img src="https://agentmods.dev/badge/skills/kkkkhazix/human-writing/human-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00257 | $0.04028 |
| Opus 5 | $0.00129 | $0.02014 |
| Sonnet 5 | $0.00051 | $0.00806 |
| Haiku 4.5 | $0.00026 | $0.00403 |
Grade A, and why
human-writing 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 11d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- human-writing — 91% identical, 40 lines differ
- human-writing — 89% identical, 30 lines differ
- human-writing — 86% identical, 51 lines differ
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
活人感写作 1.1.0
默认把文章写成一篇值得读完的中文长帖。读者应当感觉对面有一个具体的人。这个人知道一些事,也有不知道的地方。他愿意讲细节,敢下判断,偶尔岔开一句,随后还能把话接回来。
不要把“活人感”理解成口头禅、粗口、错别字和网络梗。它首先来自材料,其次来自说话位置,最后才是语气。
第一关先看作品靠什么站住
这一步先于提纲和动笔。用户要求的字数不能跳过它。
现实作品靠前两类材料,虚构作品靠第三类材料。混合创作先把两部分分开。
- 用户明确提供的经历、事实、数字、动作、原话与判断。
- 已经查到并能核验的案例、数据、产品流程、人物经历与时代条件。
- 虚构任务中,作者获准创造的事件、人物动作与场景变化。
现实稿里,模型临时想出的“比如有个人”、没有来源的典型场景、常识推演、抽象观点的后果、比喻与同义改写,都不能拿来撑篇幅。把“记录方便”“声音保留状态”“检索找回旧内容”各解释五遍,手里仍然只有三条材料。
虚构稿可以创造人物、现场和细节,不需要为它们寻找现实出处。每个主要段落或场景仍要有动作、选择、关系变化、信息变化或后果。只换景色和说法,没有事情发生,也不能拿来撑篇幅。
非虚构作品计划达到一千二百字时,先在内部逐条写出至少五件具体材料,并注明它来自用户哪句话或哪份可靠来源。只写一个概括性的类别不算。五件材料还要能组成一条实际过程,不能是五句相邻的道理。
非虚构稿列不出五件,就先别写长稿。这一轮不能输出标题和长文正文。目标字数、用户催促和“直接写”都不能把材料变多。
现实材料不够时,只能选择一种处理。
- 事实型题目有公开材料可查时,先研究,研究后重新计数。可用检索工具却没有检索,仍然算没有材料。
- 个人体验或私人判断需要用户材料,一次问完最多三个问题,此时不要同时交稿。
- 用户明确不许追问时,能研究的先研究,研究后重新计数,凑够五件就可以按原定篇幅写。研究之后仍然不足五件,缩小题目,最多交一篇六百字左右的短答。宁可明显短于目标字数,也不能用假例子和重复解释填满。
现实稿动笔前记清每件重要材料从哪里来。说不出来路的内容不能负责托住事实段落。虚构稿改为检查每个场景由哪个人物目标、动作或变化托住,不给虚构细节伪造来源。不要把这些内部检查交给用户。
现实观点稿有一种高频错误要直接拦住。用户只给“输入更方便”“声音能保留状态”“AI 可以找回旧内容”这类三条抽象想法,又要求一千多字,这仍然只有三条材料。不能分别补上用途、意义、风险和未来,再写成十几段。应当先找真实产品、使用过程、研究或用户经历。找不到就问,用户不让问而且研究后仍然不足,才写短答。
按任务读取
- 新写或大幅重写知乎回答、论坛长帖、公众号文章、博客、评论、人物稿和行业稿,读取
references/forum-prose.md。 - 真人、历史、新闻、产品、数据、评测、教程、商业信息和用户亲历,另读
references/reality.md。 - 小说、故事、虚构散文、对白和剧本,改读
references/fiction.md。用户要求帖子体小说或第一人称故事时,再同时读取references/forum-prose.md。 - 短内容、个人叙事、教程、评测、口播、演讲、剧本、对白和诗歌等形式需要特殊处理时,读取
references/formats.md。 - 初稿完成后再读取
references/revision.md。不要在动笔前加载详细审稿规则。
不要为了保险一次加载全部参考文件,只读当前任务确实命中的部分。真正的混合任务可以读取多个文件,references/revision.md 仍留到初稿以后。创作时以正向目标为主,已经写在本文件里的交付禁令留到初稿完成后再逐项检查。
多条规则同时出现时
按下面的顺序处理。
- 当前用户明确指定的文体、现实或虚构性质、语气和交付形式。
- 作品对现实作出的承诺。现实内容服从事实边界,虚构内容服从人物、因果与世界规则。
references/fiction.md、references/reality.md和references/formats.md中与当前任务直接相关的规则。references/forum-prose.md与本文件里的默认散文写法。references/revision.md的改稿规则与检查脚本的提醒。
具体文体覆盖通用写法。现实稿的来源要求不能压到纯虚构上,散文的完整主干不能压到诗歌分行和人物对白上。检查脚本只能执行已经写明的硬禁令,警告项不能替作者决定文体。
先确定作品对现实作出什么承诺
现实写作
真人、现实事件、数字、引语和用户经历都要核准。用户没提供的亲历、现场、对白和心理,不能补成事实。
What ships with it
10 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.
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.
- 11d ago First seen · 167 lines · 257 tokens per session scan A 70a6e8c92ce7
human-writing is a skill published in the GitHub repository KKKKhazix/human-writing (3,580 stars, last pushed 1mo ago), licensed MIT. It adds 257 tokens to every session and 4,028 once invoked, about $0.0013 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.
Other skills, from other repositories
novel-studio
Plan, draft, continue, revise, review, migrate, package, and create covers for short-, medium-, or long-form Chinese fiction. Use when Codex needs to start or maintain a novel project, design characters or worldbuilding, create full/volume/chapter outlines, write or repair chapters, run automated publication-readiness…
wawa-submission
A local preparation and checking tool for submitting long-form writing to Wawa Writer, a Chinese writing and submission platform. It checks author-provided files and details but does not submit them or act as an official Wawa service.
wawa-source
Import, validate, expire-check, aggregate, and redact local versioned Wawa statistics snapshots for offline dashboards. Never collect platform data, access an account, or submit content.
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.