translationese-cleaner-vi

translationese-cleaner-vi is a skill for Claude Code, Codex from longhang2004/vietnamese-humanizer. It costs 93 tokens per session (850 once invoked), scanned A, original, MIT.

A Vietnamese editing guide for making translations from English sound natural while preserving their meaning, terminology, numbers, and legal force.

In plain words
What is it for?
Use it to revise Vietnamese translations or drafts influenced by English sentence structure, especially in business, legal, academic, and technical writing.
Why use it?
It helps remove sentence patterns that are grammatically correct but unnatural in Vietnamese. It also reduces the risk of changing certainty, obligations, conditions, or technical terms while editing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to revise Vietnamese translations or drafts influenced by English sentence structure, especially in business, legal, academic, and technical writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi
Install

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.

Any agent
npx skills add longhang2004/vietnamese-humanizer --skill translationese-cleaner-vi
Clone the repo
git clone --depth 1 https://github.com/longhang2004/vietnamese-humanizer

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for translationese-cleaner-vi

README.md
[![agentmods](https://agentmods.dev/badge/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi/github.svg)](https://agentmods.dev/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi)
Your own site
<a href="https://agentmods.dev/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi"><img src="https://agentmods.dev/badge/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi/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.

agentmods 80×15 button for translationese-cleaner-vi

Your own site · 80×15
<a href="https://agentmods.dev/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi"><img src="https://agentmods.dev/badge/skills/longhang2004/vietnamese-humanizer/translationese-cleaner-vi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 850 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.00850
Opus 5 $0.00046 $0.00425
Sonnet 5 $0.00019 $0.00170
Haiku 4.5 $0.00009 $0.00085

Measured 12d ago against content hash b70b6bad226a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

translationese-cleaner-vi 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.

skills/translationese-cleaner-vi/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Làm sạch văn phong dịch Anh-Việt

Mục tiêu là câu tiếng Việt đứng được độc lập, không phải giấu nguồn dịch. Luôn phân biệt translationese với thuật ngữ chuyên ngành, quy ước hành chính và cấu trúc pháp lý có chủ đích.

Quy trình

  1. Xác định domain, độc giả, register và mức ràng buộc với bản gốc.
  2. Nếu có bản tiếng Anh, đối chiếu ý, quan hệ logic, mức chắc chắn và thuật ngữ. Nếu không có, chỉ sửa các cấu trúc có đủ ngữ cảnh.
  3. Tìm cụm danh từ dài, danh hóa, chủ ngữ giả, bị động, động từ yếu và metaphor dịch từng chữ.
  4. Xác định hành động, chủ thể và thông tin mới của từng câu. Sắp theo mạch tự nhiên của tiếng Việt thay vì giữ thứ tự tiếng Anh.
  5. Dùng động từ trực tiếp khi chính xác hơn. Tách câu nếu chuỗi bổ nghĩa khiến người đọc phải đọc lại.
  6. Rà thuật ngữ với glossary của người dùng. Khi chưa chắc, giữ thuật ngữ và nêu phương án thay thế thay vì tự quyết.
  7. Đối chiếu lại bản gốc hoặc biên bản bảo toàn.

Tra patternsfalse positives trước khi sửa văn bản pháp lý, học thuật hay kỹ thuật.

Bảo toàn

Giữ nội dung mệnh đề, quan hệ nguyên nhân, phủ định, điều kiện, mức nghĩa vụ, mức chắc chắn, số liệu và thuật ngữ. Không biến "may" thành "sẽ", "shall" thành "nên", hay "associated with" thành quan hệ nhân quả.

Không thay một cụm chung bằng cơ chế, metric hoặc ví dụ cụ thể nếu thông tin đó không nằm trong input hay context được cung cấp.

Nếu một metaphor tiếng Anh có nhiều cách hiểu, dùng diễn đạt trung tính giữ đúng chức năng hoặc hỏi lại. Không thêm ví dụ bản địa để lấp chỗ trống.

Nguyên tắc biên tập

  • "Thông qua việc" không sai mặc định; chỉ thay khi động từ trực tiếp đủ nghĩa.
  • Bị động hợp lệ khi tác nhân không biết, không quan trọng hoặc cần tránh nêu vì lý do chuyên môn.
  • Từ Hán-Việt phù hợp có thể chính xác hơn từ thuần Việt, nhất là trong luật, y khoa và hành chính.
  • Giữ tên tính năng, slogan và thuật ngữ đã được phê duyệt, trừ khi người dùng cho phép đổi.
  • Không giữ một ẩn dụ dịch sát nếu người Việt khó suy ra nghĩa thực tế.

Read the full file on GitHub · 54 lines

Files

What ships with it

4 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.

Changes

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.

  1. 12d ago First seen · 54 lines · 93 tokens per session scan A b70b6bad226a

Subscribe to this mod's changes

translationese-cleaner-vi is a skill published in the GitHub repository longhang2004/vietnamese-humanizer (45 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 850 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

website-maintainer

Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.

yamadashy/repomix · 37 tokens

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.

laolaoshiren/claude-code-skills-zh · 33 tokens

security-review

Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…

waybarrios/opencode-power-pack · 64 tokens

codeql

Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.

waybarrios/opencode-power-pack · 42 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens

feature-dev

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…

waybarrios/opencode-power-pack · 62 tokens