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-polishgit 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-polish)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/punct-polish"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/punct-polish/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-polish"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/punct-polish.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 | $0.00164 | $0.01992 |
| Opus 5 | $0.00082 | $0.00996 |
| Sonnet 5 | $0.00033 | $0.00398 |
| Haiku 4.5 | $0.00016 | $0.00199 |
Grade A, and why
punct-polish 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标点打磨
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……一次性解决。
AI最常犯的标点错误
按频率排序：
- 半角逗号 → 该用
，的地方写了,— 极高频率 - 半角句号 → 该用
。的地方写了.— 极高频率 - 缺少中西空格 →
使用React构建应该是使用 React 构建— 高频率 - 直引号 →
"你好"应该是「你好」（非代码） — 高频率 - 半角括号 →
见下图(图1)应该是见下图（图1）— 高频率 - 破折号滥用 →
——即应该是，即或直接删除 — 中等 - 省略号不规范 →
....或。。。应该是……— 中等 - 顿号误用 →
苹果，香蕉应该是苹果、香蕉— 中等 - 感叹号连用 →
太棒了！！！应该是太棒了！— 中等 - 多余中西空格 →
这 是 中 文应该是这是中文— 低 - 英文标点混入中文 →
Hello, world（中文语境） — 低 - 中文标点混入英文 →
This is good。— 低
其中前5项全自动修正，后7项根据上下文判断后修正或标记建议人工复核。
四种场景的标点规则
中文散文（公众号/博客/随笔）
全角标点强制使用：，。？！：；（）「」『」『。破折号禁用，用逗号或句号替代。省略号用六个点……。顿号分隔中文并列短词。感叹号全文不超过3处，禁止连用。
技术文档（API/手册/Runbook）
中文和英文/数字之间加空格：使用 React 构建、调用 API 接口。代码围栏内的标点完全不动。行内代码的标点不动。URL不动。数字不动：1,000、3.14、12:30。标题层级#→##→###不超过三级。
中英混排（双语发布/国际化）
中文块与英文块之间加空格。中文括号内嵌英文时，括号用全角，内部英文标点用半角。英文块内嵌中文时，英文标点用半角，内部中文标点用全角。
术语一致性：首次出现保留英文+中文注解，后续统一用中文。行业通用缩写（SFT/RL/MoE）全程保留。
有稳定中文对译的英文词直接换成中文：context→上下文、state→状态、cache→缓存、claim→断言、runtime→运行时、contract→契约。
社交媒体（小红书/即刻/推特）
适度灵活：允许适度使用emoji（每段不超过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，中文英文间仍需空格，不能连续3个以上感叹号。
英文标点校对
英文标点的自动修正：
- 逗号后空格：
a,b→a, b - 句号后空格：
end.Start→end. Start - 引号方向：直引号
"→弯引号"'（非代码） - 破折号：
---→—--→– - 省略号：
...→… - 首字母大写：句首单词
- 连续空格合并
英文AI词汇替换：delve→examine、leverage→use、utilize→use、robust→strong、streamline→simplify、harness→use、navigate→handle、unpack→explain、paradigm→system、synergy→combination、tapestry→mix、landscape→situation、game-changer→significant、moving forward→next。
代码/机器可读内容保护
以下区域标点100%不动：
- 代码围栏
```和行内代码 - URL、邮箱、文件路径
- 数字：千分位
1,000、小数3.14、时间12:30 - HTML/XML标签
<div> - 命令行参数
--flag - JSON键名
"key": "value"
执行流程
先识别场景，再标记保护区域，然后扫描检测，最后分层修正。
- 场景识别：含代码块/URL/参数→技术文档；中英混排>30%→双语；含@/#/emoji→社交媒体；默认→中文散文
- 保护标记：标记代码围栏、行内代码、URL、邮箱、数字、英文缩写
- 检测扫描：快速扫描半角标点和中西空格→深度扫描破折号/省略号/感叹号→上下文判断顿号和引号
- 分层修正：自动修正80%（半角→全角、空格补全）→建议修正15%（顿号、引号方向）→人工复核5%（语义模糊项）
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.
- 11d ago First seen · 159 lines · 164 tokens per session scan A b90e09ea35c8
punct-polish is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 23d ago), licensed MIT. It adds 164 tokens to every session and 1,992 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.