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 Kihara777/NixKits --skill translate-pseudocngit clone --depth 1 https://github.com/Kihara777/NixKitsWrote 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/kihara777/nixkits/translate-pseudocn)<a href="https://agentmods.dev/skills/kihara777/nixkits/translate-pseudocn"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/translate-pseudocn/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/kihara777/nixkits/translate-pseudocn"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/translate-pseudocn.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 | $0.00069 | $0.01828 |
| Opus 5 | $0.00034 | $0.00914 |
| Sonnet 5 | $0.00014 | $0.00366 |
| Haiku 4.5 | $0.00007 | $0.00183 |
Grade A, and why
translate-pseudocn 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
伪中国语翻译
为 NixKits 文档体系提供 pcn（伪中国语）语言。
自动发现契约
write-project-docs / write-maintenance-log 通过扫描 skills/translate-*/SKILL.md frontmatter 自动发现：
| 字段 | 值 | 用途 |
|---|---|---|
language_code |
pcn |
目录名、文件扩展名 |
display_name |
偽中国語 |
语言切换器标签 |
base_language |
ja |
源语言 |
设计原则
伪中国语是日语文本剥离假名后的视觉结果，不是中文翻译。
- 基于智能体自然语言理解进行转换，不使用自动化脚本/正则替换。理解句子结构后再做转换。
- 语序转换为中文语序（SOV → SVO）
- 日文汉字名词保持原样
- 片假名外来语优先查词典映射为日本汉字，未命中则剥离
- 禁止使用简体中文或繁体中文汉字（如「软件」「安装」「模块」）
替换规则
1. 剥离假名
去除所有平假名（あ-ん）。片假名（ア-ン）按以下优先级处理：
- 查
dictionary.md映射为日本汉字 - 未命中 → 剥离（仅保留上下文中的日文汉字）
2. 保留日文汉字
日文汉字名词原样保留，包括：
| 示例 | 保留形式 | 说明 |
|---|---|---|
| 開発 | 開発 | 日文汉字，非「开发」 |
| 環境 | 環境 | 日文汉字 |
| 管理 | 管理 | 日文汉字 |
| 提供 | 提供 | 日文汉字 |
| 設定 | 設定 | 日文汉字 |
| 情報 | 情報 | 日文汉字 |
3. 保留日语语序
日语 SOV 语序转换为中文 SVO 语序（主-动-宾）。
4. 助词转换（最小化）
助词适当保留以增加文本丰富性，仅剥离无实义的语法标记：
| 日文 | 変換 | 条件 |
|---|---|---|
| の | 之 | 所有/所属 |
| と | 與 | 并列连接 |
| に | 於 | 方向/目标 |
| で | 以 | 手段/场所 |
| から | 自 | 起点 |
| まで | 至 | 终点 |
| は | (剥离) | 主题标记，无实义 |
| が | (剥离) | 主语标记，无实义 |
| を | (剥离) | 宾语标记，无实义 |
5. 标点
日文标点保持原样（、 。 不转换）。
6. 代码块保护
- Nix 代码块：仅翻译
#注释行 - Bash 代码块：全部不动
- 先按
```边界提取代码块，仅对非代码区域应用规则
验证
翻译完成后，使用以下脚本检查输出文件是否残留假名：
import re
def check_kana(path):
with open(path) as f:
text = f.read()
blocks = re.split(r'```', text)
outside = ''.join(blocks[i] for i in range(0, len(blocks), 2))
kata = re.findall(r'[\u30A0-\u30FF]{2,}', outside)
hira = re.findall(r'[\u3040-\u309F]{2,}', outside)
if kata: print(f'残片假名: {kata}')
if hira: print(f'残平假名: {hira}')
词典
片假名→日本汉字映射见 dictionary.md。仅包含有对应日本汉字词的片假名外来语。
注意事项
- 伪中国语是视觉伪本地化，外观是「汉字+符号」的日文文本
- 禁止使用简体中文汉字（如「软件」「安装」「模块」「设置」）
- 语言切换器生成：从日文源提取路径逐个精确构造
日本語→[日本語]（加链接），自身标签偽中国語（纯文本）- 验证发现的残留片假名应立即翻译并加入
dictionary.md，然后重新生成所有 pcn 文档
常见陷阱与修复（实战经验）
1. 片假名词典映射必须优先于剥离
所有片假名在剥离前必须先查词典。常见遗漏项及对应日文汉字：
What ships with it
1 file 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.
- 12d ago First seen · 161 lines · 69 tokens per session scan A 4d94af0aa026
translate-pseudocn is a skill published in the GitHub repository Kihara777/NixKits (25 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,828 once invoked, about $0.0003 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
china-translate
A Chinese-English translation and localisation guide for technical text and product interfaces. Localisation means adapting wording and cultural references so they sound natural to users in the target language.
content-translator
Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support for teams working across language barriers.
translator
Translate text between 100+ languages with automatic source detection. Use when: the user asks to translate text, detect a language, or work with multilingual content. NOT for: translating code/documentation in bulk, summarization, or rewriting text in the same language.
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Chinese (FunASR/Whisper), English (Whisper), Hebrew (ivrit.ai), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.