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 punct-mastergit 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/punct-master)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/punct-master"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/punct-master/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/punct-master"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/punct-master.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 | $0.00153 | $0.02452 |
| Opus 5 | $0.00077 | $0.01226 |
| Sonnet 5 | $0.00031 | $0.00490 |
| Haiku 4.5 | $0.00015 | $0.00245 |
Grade A, and why
punct-master 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 10d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标点大师（Punct Master）
AI写中文，标点是最常见的毛病：半角逗号、缺少中西空格、直引号、破折号滥用……本技能一次性解决。
12类AI常见标点错误谱系
| # | 错误类型 | 错误示例 | 正确写法 | 自动修正 |
|---|---|---|---|---|
| 1 | 半角逗号 | 今天,明天 |
今天，明天 |
✅ |
| 2 | 半角句号 | 这是一本书. |
这是一.book。 |
✅ |
| 3 | 半角引号 | "你好" |
「你好」 |
✅非代码 |
| 4 | 半角括号 | 见下图(图1) |
见下图（图1） |
✅ |
| 5 | 缺少中西空格 | 使用React构建 |
使用 React 构建 |
✅ |
| 6 | 多余中西空格 | 这 是 中 文 |
这是中文 |
✅ |
| 7 | 破折号滥用 | ——即 |
，即 或删除 |
✅ |
| 8 | 省略号不规范 | .... 。。。 |
…… |
✅ |
| 9 | 顿号误用 | 苹果，香蕉 |
苹果、香蕉 |
⚠️建议 |
| 10 | 感叹号连用 | 太棒了！！！ |
太棒了！ |
✅ |
| 11 | 英文标点混入中文 | Hello, world（中文语境） |
Hello，world |
⚠️建议 |
| 12 | 中文标点混入英文 | This is good。 |
This is good. |
⚠️建议 |
四类场景规则矩阵
场景A：中文散文（公众号/博客/随笔）
全角标点强制：，。？！：；（）「」『」『
引号规范：直角引号「」用于概念和对话
破折号：禁用（用逗号/句号/括号替代）
省略号：六个点 ……
顿号：分隔中文并列短词
感叹号：全文≤3处，禁止连用
场景B：技术文档（API/手册/Runbook）
中西文间空格：使用 React 构建 / 调用 API 接口
代码围栏保护：不修改 ``` ``` 内的任何标点
行内代码保护：不修改 ` ` 内的标点
URL保护：不修改 http://... 内的标点
数字保护：1,000 / 3.14 / 12:30 不动
标题层级：# → ## → ### 不超过三级
场景C：中英混排（双语发布/国际化）
排版规则：
- 中文块与英文块之间加空格
- 中文括号内嵌英文：括号全角，内部英文标点半角
- 英文块内嵌中文：英文标点半角，内部中文标点全角
术语一致性：
- 首次出现：保留英文+中文注解
- 后续出现：统一用中文
- 行业通用缩写（SFT/RL/MoE）全程保留
场景D：社交媒体（小红书/即刻/推特）
适度灵活：
- 允许适度使用emoji（每段≤2个）
- 允许适度使用感叹号（表达情绪）
- 允许使用---分隔线
但仍有底线：
- 中文不能用半角标点
- 中西文间仍需空格
- 不能连续3个以上感叹号
英文标点总编辑能力
| 检查项 | 规则 | 修正方式 |
|---|---|---|
| 逗号后空格 | a,b → a, b |
自动 |
| 句号后空格 | end.Start → end. Start |
自动 |
| 引号方向 | 直引号 " → 弯引号 " ' |
自动（非代码） |
| 破折号 | --- → — -- → – |
自动 |
| 省略号 | ... → … |
自动 |
| 首字母大写 | 句首单词大写 | 自动 |
| 连续空格 | word1 word2 → word1 word2 |
自动 |
英文禁止词：delve、leverage（as verb）、utilize、robust、streamline、harness、navigate（challenges）、unpack、paradigm、synergy、tapestry、landscape、game-changer、moving forward
代码/机器可读内容保护
保护清单（100%不动）：
- 代码围栏 ``` ... ```
- 行内代码 `...`
- URL http://... https://...
- 邮箱 [email protected]
- 文件路径 a/b/c.ext
- HTML/XML标签 <div>
- 数字 1,000 / 3.14 / 12:30
- 命令行参数 --flag
- JSON键名 "key": "value"
保护策略：
- 上述区域内标点100%不动
- 区域外按场景规则处理
- 边界处上下文判断
What ships with it
3 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.
- 10d ago First seen · 240 lines · 153 tokens per session scan A d49e7fe0ea18
punct-master is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 22d ago), licensed MIT. It adds 153 tokens to every session and 2,452 once invoked, about $0.0008 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
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
qu-ai-wei
A tool for rewriting Simplified Chinese so it sounds more natural while keeping the original facts, meaning, evidence strength, tone, and authorial voice.
turkce-humanizer
Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını yerleştirir. "Türkçeleştir," "AI kokusunu at," "bu Türkçe metni doğallaştır," "humanize et" gibi ifadelerle veya AI-üretimi görünen Türkçe paragraf sunulduğunda tetiklenir.
chinese-typography
A Chinese typography guide for websites, articles, social-media posts, PDFs, Word documents, and presentations. It explains spacing, fonts, line height, punctuation, and line breaking for Chinese text.
accent-dial
Skill "accent-dial" from petar-djukic/writing-skills, covering accent dial (pre-terminal stage), usage, calibration (strategy theatre payload, 2026-08-21), sentence grain (default since gh-73) and the review gate (mandatory).
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.