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-business-commsgit 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-business-comms)<a href="https://agentmods.dev/skills/trussary/vietnamese-language-skill/vietnamese-business-comms"><img src="https://agentmods.dev/badge/skills/trussary/vietnamese-language-skill/vietnamese-business-comms/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-business-comms"><img src="https://agentmods.dev/badge/skills/trussary/vietnamese-language-skill/vietnamese-business-comms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00151 | $0.02059 |
| Opus 5 | $0.00076 | $0.01030 |
| Sonnet 5 | $0.00030 | $0.00412 |
| Haiku 4.5 | $0.00015 | $0.00206 |
Grade A, and why
vietnamese-business-comms 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vietnamese marketing and sales copy (vi-VN)
Campaign and outbound copy fails in two directions at once. It fails commercially by reading as a mass mailing — wrong pronoun, translated CTA, formal vocabulary where the market uses loanwords. And it fails legally, because Vietnamese advertising law regulates ordinary marketing enthusiasm: unproven superlatives, discounts over 50%, messages sent outside the legal window, and, from 01/01/2026, undisclosed influencer content.
Both failures are invisible to a fluency check. Every rule below exists to stop a specific one.
Step 1 — The channel picks the register, not the brand
Vietnamese has no neutral "you", and in this skill the choice is made by where the message lands rather than by the brand's usual voice.
| Channel or genre | Register | Address |
|---|---|---|
| Zalo ZNS/ZBS template | zns |
Quý khách — even for a brand that says bạn everywhere else |
| B2B cold email, quote, proposal, dunning | b2b |
anh/chị, self as em or tôi |
| E-commerce, social, ads, push | saas |
bạn |
| Mid-market services, consulting | consult |
anh/chị |
| Press release | press |
Institutional third person, Quý vị if anyone |
| Livestream script | livestream |
cả nhà, mọi người — spoken register |
bạn in B2B outreach is the single clearest tell of an automated send. No Vietnamese
salesperson opens a cold email with Chào bạn.
Who you are in the sentence — em versus tôi, and why age outranks job title —
references/b2b-xung-ho.md. The shared pronoun matrix:
references/register-matrix.md.
Step 2 — Core rules (non-negotiable, no file hop needed)
- Never
bạnormìnhin B2B outreach, a quote, or a dunning notice.anh/chịfor them;emif you are plausibly junior,tôiotherwise. - Open with courtesy, not with the pitch. Vietnamese cold outreach puts a line of context before the ask. An English-style first-line value proposition reads rude.
- Never write
nhất,số 1,duy nhất,hàng đầu,bán chạy nhấtas an unproven claim. Illegal under Điều 8 khoản 11 Luật Quảng cáo 16/2012/QH13, with current fines.bán chạy nhấtis a ranking claim like any other. - A discount over 50% needs a registered
chương trình khuyến mại tập trung. NĐ 81/2018 as amended by NĐ 128/2024. A headline number over 50 is a compliance question. - No marketing content in a transactional Zalo template. It gets the template rejected. ZNS/ZBS bodies cap at 400 characters có dấu.
- Advertising messages need prior opt-in, a working opt-out, and the legal window — SMS 07:00–22:00, calls 08:00–17:00, ≤3 SMS and ≤1 call per number per 24h.
- Use market vocabulary, not formal translations.
Freeship,Deal,Voucher,Mua ngay.Học thêmmeans take extra classes and is never a CTA. - Never name a competitor in a comparison, and never use a person's image, name, or words without consent.
What ships with it
15 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/bao-gia.md.template 1.8 KB
- references/b2b-xung-ho.md 6.0 KB
- references/banned-phrases.md 4.5 KB
- references/channel-guide.md 5.1 KB
- references/compliance.md 5.3 KB
- references/examples.md 11 KB
- references/glossary.md 5.0 KB
- references/locale-formatting.md 6.9 KB
- references/promo-law.md 4.7 KB
- references/qa-checklist.md 4.3 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/rules_business.py 8.0 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 · 142 lines · 151 tokens per session scan A df416b2d9908
vietnamese-business-comms is a skill published in the GitHub repository trussary/vietnamese-language-skill (77 stars, last pushed 9d ago), licensed MIT. It adds 151 tokens to every session and 2,059 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
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.