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 trussary/vietnamese-language-skill --skill vietnamese-landing-copygit clone --depth 1 https://github.com/trussary/vietnamese-language-skillWrote 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/trussary/vietnamese-language-skill/vietnamese-landing-copy)<a href="https://agentmods.dev/skills/trussary/vietnamese-language-skill/vietnamese-landing-copy"><img src="https://agentmods.dev/badge/skills/trussary/vietnamese-language-skill/vietnamese-landing-copy/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/trussary/vietnamese-language-skill/vietnamese-landing-copy"><img src="https://agentmods.dev/badge/skills/trussary/vietnamese-language-skill/vietnamese-landing-copy.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 | $0.00137 | $0.01903 |
| Opus 5 | $0.00068 | $0.00951 |
| Sonnet 5 | $0.00027 | $0.00381 |
| Haiku 4.5 | $0.00014 | $0.00190 |
Grade A, and why
vietnamese-landing-copy 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vietnamese landing-page copy (vi-VN)
Vietnamese is a low-resource language for LLMs. Left unguided, output defaults to English-calqued translationese: fluent-sounding but obviously machine-written. It picks the wrong pronoun, translates CTAs word-for-word, writes illegal advertising superlatives, and formats currency the American way. Every rule below exists to stop a specific, observed defect.
Step 1 — Pick the register before writing a single word
Vietnamese has no neutral "you." The pronoun is the first decision, not a detail.
| Audience | Address the reader as | Vocabulary |
|---|---|---|
| Real estate, finance, luxury, airlines, healthcare | quý khách |
Hán-Việt heavy, ornate |
| Institutional, government, broadcast announcements | quý vị |
Formal, plural |
| Sales consulting, mid-market services, local business | anh/chị |
Warm, respectful |
| SaaS, tech, e-commerce, youth brands | bạn |
Thuần Việt, terse |
| Policy, terms, descriptive prose (never direct address) | khách hàng |
Neutral 3rd person |
If the brief does not say, infer from the product. A căn hộ cao cấp page is quý khách.
A developer tool is bạn. Never mix two registers in one page — that is the single most
visible amateur tell.
Full pronoun matrix, including the registers the other Vietnamese skills use: references/register-matrix.md. The Hán-Việt vs thuần Việt prestige axis, classifiers, and the section-order house style: references/register-guide.md
Step 2 — Core rules (non-negotiable, no file hop needed)
- Emit NFC Unicode. Precomposed
ế(U+1EBF), never base + combining marks. NFD breaks web font rendering and string length. Normalize everything you output. - Pick one tone-mark style and hold it for the whole document. Default to kiểu mới
(
hoà,thuỷ,khoẻ) matching post-2022 Bộ GD&ĐT textbooks. Kiểu cũ (hòa,thủy,khỏe) is equally correct and still dominant commercially — match the client's existing site when there is one. Neither is wrong. Inconsistency within one page is the defect. - Modifier follows the noun.
căn hộ cao cấp, nevercao cấp căn hộ. - Recast English passives.
được thiết kế bởi X→do X thiết kế, or make it active:X kiến tạo. - Never write
số 1,tốt nhất,duy nhất,hàng đầuas an unproven claim. This is illegal under Điều 8 khoản 11 Luật Quảng cáo 16/2012/QH13, not merely tacky. Real fines, currently issued. See references/banned-phrases.md. - Vietnamese has no grammatical plural. ICU messages take only
other. Anone {}branch invi.jsonis always a bug. - Write CTAs from the conventional list, not from the English.
Learn moreisTìm hiểu thêm, neverHọc thêm.
What ships with it
13 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.
- assets/vi.json.template 7.5 KB
- references/banned-phrases.md 6.4 KB
- references/compliance.md 5.3 KB
- references/examples.md 11 KB
- references/glossary.md 5.9 KB
- references/legal-copy.md 4.4 KB
- references/locale-formatting.md 6.9 KB
- references/qa-checklist.md 3.2 KB
- references/register-guide.md 5.6 KB
- references/register-matrix.md 5.2 KB
- references/unicode-and-tone.md 2.8 KB
- scripts/check_font_coverage.py 8.3 KB runs code
- scripts/validate_copy.py 34 KB runs code
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 · 141 lines · 137 tokens per session scan A f68a8865a568
vietnamese-landing-copy is a skill published in the GitHub repository trussary/vietnamese-language-skill (77 stars, last pushed 9d ago), licensed MIT. It adds 137 tokens to every session and 1,903 once invoked, about $0.0007 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
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.