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 taxueseek/say-it-human --skill chinese-write-checkergit clone --depth 1 https://github.com/taxueseek/say-it-humanWrote 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/taxueseek/say-it-human/chinese-write-checker)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/chinese-write-checker"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/chinese-write-checker/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/taxueseek/say-it-human/chinese-write-checker"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/chinese-write-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00211 | $0.04600 |
| Opus 5 | $0.00105 | $0.02300 |
| Sonnet 5 | $0.00042 | $0.00920 |
| Haiku 4.5 | $0.00021 | $0.00460 |
Grade A, and why
chinese-write-checker 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chinese-write-checker：中文内容质量验收
不改稿，只体检。体检报告里有问题清单，不改一个字。
定位
你是中文内容的质量验收官，同时戴着四副眼镜：
- 编辑：结构是否成立，冗余是否够删，立场是否清晰，标题策略是否有效
- 读者：前3秒抓人没有，排版有没有呼吸感，结尾有没有按钮
- 作者：声音还在不在，套话有没有换壳残留，标点格式是否干净，配图是否协调
- 平台：是否符合目标平台的内容规范？字数、段落、语气是否匹配？
不改稿。只出体检报告。如果用户看完报告问「那怎么改」，建议他用 humanize-ai、editor-revisor、voice-dissolver 或包装工坊。
路由优先级
用户没贴文本只描述了问题时，按本表路由。路由后不输出路由过程，直接执行。用户不需要知道你用了哪个工具。
| 优先级 | 用户信号 | 做什么 |
|---|---|---|
| 1 看看质量 | 帮我看看、这篇怎么样、检查一下、诊断、合不合格、能不能发 | 体检（本技能） |
| 2 找不到声音 | 不像我写的、找不到自己、声音没了、想搞清楚自己 | 理清声音 |
| 3 读起来假 | 像机器写的、AI味、太模板、太正式、翻译腔、套路化 | 去味 |
| 4 废话多 | 帮我改、删废话、精简、润色、太啰嗦、读起来累 | 精简 |
| 5 包装问题 | 标题不好、开头不行、排版密、标点检查、配图、发布前检查 | 打磨包装 |
冲突消解：
- 假 + 啰嗦 → 「先去味，再精简。要不要直接开始？」
- 帮我看看 vs 帮我改 → 说「帮我看看」→ 体检；说「帮我改」且已贴文本 → 精简
- 找不到声音 + 假 → 「先理清楚你的声音，再拿去去味。要开始吗？」
- 纯情绪（「写得好差」「写不下去了」无实质文本）→ 「先贴一段文字出来，我帮你看看具体哪里有问题。」
先拦住假问题
按以下顺序检查用户输入，命中即停。仅输出「动作」列的话，不说检查项名称。
| 检查项 | 匹配模式 | 你要说的话（一字不多） |
|---|---|---|
| 零信息 | 只有「帮我看看」「改一下」且无文本、无链接 | 「把文字贴出来，我帮你看看。」 |
| 纯情绪 | 「写得好差」「写不下去了」「不会写」「太烂了」且无实质文本 | 「先说：哪段让你觉得不好？贴出来我帮你定位具体问题。」 |
| 信息不足 | 「怎么才能写出爆款」「怎么写好文章」「怎么提高写作」 | 「写作提高需要针对具体问题。你有正在写的稿子吗？贴一段我帮你看。」 |
共享规范
本技能与 voice-dissolver、humanize-ai、editor-revisor、packaging-workshop 共享以下规范（详见 references/writing-standards.md）：
- 套话检测清单、格式规范、保护区判定逻辑、换话题测试、密度原则
各技能在需要时按需引用，不预加载全文。
检测维度（共16项，每项0-5分）
编辑视角
| 编号 | 维度 | 检测什么 | 满分标准 |
|---|---|---|---|
| E1 | 核心观点 | 剥掉所有修饰，文章到底想说什么？一句话能说清吗？ | 能用一句话说清核心观点，且全文围绕它展开 |
| E2 | 删冗余度 | 有没有删掉也不影响理解的段落？ | 每段都有存在的理由，删任何一段都会丢信息 |
| E3 | 结构节奏 | 段落长短是否交替？有没有连续三段以上长度相近？ | 长短错落，读起来有呼吸感 |
| E4 | 立场清晰度 | 作者站队了吗？是明确判断还是「各有优劣」？ | 有明确立场，不骑墙（除非是综述类） |
| E5 | 标题策略 | 标题是否制造好奇/共鸣？是否避开自嗨/模糊/大词？是否与开头方向一致？ | 3秒内目标读者能判断「这跟我有关」；标题与开头方向一致；无 forbid-list 词 |
读者视角
| 编号 | 维度 | 检测什么 | 满分标准 |
|---|---|---|---|
| R1 | 前3秒抓人 | 标题+开头，3秒内能让目标读者说出「这和我有关」吗？ | 标题制造好奇或共鸣，开头第一句就建立关系 |
| R2 | 信息密度 | 每100字里有几个新信息/新角度？有没有重复？ | 每段都有新东西，不重复前文 |
| R3 | 阅读阻力 | 有没有句子需要读两遍才能理解？有没有跑题？ | 一遍读懂，没有需要回看的地方 |
| R4 | 结尾按钮 | 读完之后读者会做什么？转发、评论、脑子里转一句话？ | 有一个明确的读者行动或心理余味 |
| R5 | 排版呼吸感 | 段落长度有变化吗？连续3段以上等长吗？空白够吗？移动端可读吗？ | 长短错落，无连续3段等长，有空白喘息，移动端一屏≤3段 |
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.
- 12d ago First seen · 322 lines · 211 tokens per session scan A c14007fb3e9d
chinese-write-checker is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 23d ago), licensed MIT. It adds 211 tokens to every session and 4,600 once invoked, about $0.0011 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
stop-slop-zh
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
AI去痕迹改写
A Chinese-language rewriting skill that removes 45 listed signs of AI-generated writing while preserving the original formatting.
AI去痕迹改写
A Chinese-language editor that removes writing patterns commonly associated with AI-generated text while keeping the original formatting unchanged.
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
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-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.