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 YYC-Cube/YYC3-i18n-Core --skill i18n-qualitygit clone --depth 1 https://github.com/YYC-Cube/YYC3-i18n-CoreWrote 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/yyc-cube/yyc3-i18n-core/i18n-quality)<a href="https://agentmods.dev/skills/yyc-cube/yyc3-i18n-core/i18n-quality"><img src="https://agentmods.dev/badge/skills/yyc-cube/yyc3-i18n-core/i18n-quality/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/yyc-cube/yyc3-i18n-core/i18n-quality"><img src="https://agentmods.dev/badge/skills/yyc-cube/yyc3-i18n-core/i18n-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.00754 |
| Opus 5.5 | $0.00009 | $0.00302 |
| Sonnet 5.5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
i18n-quality 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 yesterday.
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.
What it actually says
i18n-quality — 翻译质量评估与术语合规
你是翻译质量评审助手，遵循 @yyc3/i18n-core（YYC³）约定：对「源文案 ↔
译文」对逐条评分（确定性规则引擎，非主观打分），并核对术语表强制词条。
前置条件
- 引擎：
@yyc3/i18n-core≥ 3.3.0。 - 输入：源文案、译文、源/目标语言标签（BCP-47）。
- 术语合规（可选）：项目配置
Glossary（enforced 词条 + 目标语言标准译名）。
工作流
- 评分（二选一）：
- MCP 工具：
quality_score { sourceText, translatedText, sourceLocale, targetLocale }。 - 脚本直连：
node skills/i18n-quality/scripts/quality.mjs <source> <translation> --sl en --tl ja（--threshold百分制，默认 80；退出码 0/1 即通过与否）。
- MCP 工具：
- 术语核对：
glossary_lookup { mode: "exact", term }查词条；{ mode: "locale", locale }列该语言全部 enforced 译名。- enforced 词条在译文中被违反时，按标准译名改写后重跑第 1 步。
- 批量：整包评估用
quality_report（引擎全量键值对扫描）。 - 判定：
passed: false、分数低于项目阈值（百分制，建议 ≥ 80）或 存在术语违规即不通过。
红线
- 评分是确定性规则输出（长度比/占位符完整性/标点规范等）——不得 主观调分；规则外问题在报告中单列人工复核。
- 占位符（
{name}、ICU 参数）缺失或多余属于 critical 级问题。 - 术语 enforced 违规不因「译文更流畅」而豁免。
报告格式
{ "score": 75, "passed": false, "issues": [{ "ruleId": "placeholder-mismatch", "severity": "critical" }] }
示例
源 Hello {name} ↔ 译 こんにちは（--sl en --tl ja）→
占位符 {name} 缺失，placeholder-mismatch critical 级，评分 75/100、
passed: false，判定不通过（exit 1）；补占位符后复评。
© 2026 YanYuCloudCube™（YYC³）· [email protected] · MIT
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.
- yesterday First seen · 61 lines · 22 tokens per session scan A 6d9695216c1e
i18n-quality is a skill published in the GitHub repository YYC-Cube/YYC3-i18n-Core (0 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 754 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-05.
Other skills, from other repositories
iflytek-text-proofread
A tool that checks Chinese writing through iFlytek’s official document-proofreading service. It looks for spelling, punctuation, wording, factual, terminology, and sensitive-content problems.
iflytek-translate
A text-translation tool that uses iFlytek's machine-translation service and supports more than 70 language pairs. It can translate text supplied directly, through standard input, or from a file.
iflytek-video-translate
A tool that translates a video’s speech into another language and creates dubbed audio. Video localization means adapting video content for viewers who speak a different language.
tongwen
Use when translating engineering DWG drawings with Tongwen — TWEXTRACTALL / TWTRANSLATE / TWWRITEBACKFILE in AutoCAD 2019/2021/2025/2026, glossary CSV with CM/TM precedence, placeholder QA blocking write-back, or headless Tongwen.Runner.BatchCli -i -o -c -m runs; also when extraction fails with a Named Pipe connection…
backend-internationalization
Use this skill when implementing multi-language support, translation workflows, or locale-aware formatting. This skill enforces: BCP 47 locale tags, ICU MessageFormat for complex messages, dot-separated namespaced keys, fallback chains, and CI-validated translation files. Applies to any backend stack serving…
thai-resume
Use this skill for any task involving Thai-language or bilingual (TH/EN) resumes and CVs. Trigger whenever the user asks to: write a Thai resume, draft a CV in Thai, build a bilingual Thai-English resume, format an application for a Thai employer, choose between พ.ศ. and ค.ศ. dates in a CV, or tailor a resume for…