expert-translator

expert-translator is a skill for Claude Code, Codex from Day1Labs/OpenAva. It costs 30 tokens per session (515 once invoked), scanned A, original, MIT.

A translation workflow that turns source text into polished writing in another language while keeping its meaning, tone, glossary terms, and formatting intact.

In plain words
What is it for?
Use it to translate documents, Markdown, lists, tables, links, or other formatted text into a chosen language and style.
Why use it?
It reduces missing details, inconsistent terminology, awkward phrasing, and formatting changes that can occur during translation.

Skill for Claude CodeCodex

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

Good fit Use it to translate documents, Markdown, lists, tables, links, or other formatted text into a chosen language and style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/day1labs/openava/expert-translator
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 Day1Labs/OpenAva --skill expert-translator
Clone the repo
git clone --depth 1 https://github.com/Day1Labs/OpenAva

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 expert-translator

README.md
[![agentmods](https://agentmods.dev/badge/skills/day1labs/openava/expert-translator.svg)](https://agentmods.dev/skills/day1labs/openava/expert-translator)
Your own site
<a href="https://agentmods.dev/skills/day1labs/openava/expert-translator"><img src="https://agentmods.dev/badge/skills/day1labs/openava/expert-translator.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 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 $0.00030 $0.00515
Opus 5 $0.00015 $0.00258
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 7d ago against content hash 1be9ae5f0fb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

expert-translator 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 7d 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.

OpenAva/Runtime/Agent/Skills/expert-translator/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert Translator

Use this skill for high-quality translation tasks where accuracy, natural phrasing, style control, and format integrity all matter.

Inputs

  • source_text: The original text to translate.
  • target_language: The destination language, such as Chinese, English (US), or English (UK).
  • style_and_tone: The target style, such as Academic, Business Professional, Casual and Humorous, or Literary and Elegant.
  • glossary (optional): A key-value map of terms that must be translated consistently.

Workflow

  1. Analyze the request and identify the target language, required tone, domain vocabulary, and any glossary constraints.
  2. Produce an initial translation that stays fully faithful to the source text.
  3. Review the draft against the source for accuracy, omissions, additions, fluency, terminology consistency, and style alignment.
  4. Refine the translation so it reads like original writing in the target language while preserving the source meaning.
  5. Return only the final polished translation unless the user explicitly asks for supporting notes.

Translate Rules

  • Preserve original formatting exactly, including Markdown, lists, tables, links, emphasis, LaTeX, code fences, and YAML frontmatter.
  • Do not translate locked zones such as code blocks, inline code, URLs, and YAML frontmatter keys.
  • Apply glossary terms exactly when they appear.
  • Prefer semantic fidelity first, then improve phrasing during refinement.

Review Checklist

  • Accuracy: no mistranslations, omissions, or added meaning.
  • Fluency: no awkward literal phrasing or translationese.
  • Style: matches the requested audience and tone.
  • Terminology: glossary usage is correct and consistent.
  • Format integrity: all formatting and locked zones remain intact.

Output Rules

  • Default output is only the final translated text.
  • Do not expose internal reasoning, step-by-step analysis, or review notes.
  • If the user explicitly asks for glossary usage or a diff list, append a short clearly labeled section after the translation.

Read the full file on GitHub · 53 lines

Files

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.

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. 7d ago First seen · 53 lines · 30 tokens per session scan A 1be9ae5f0fb0

Subscribe to this mod's changes

expert-translator is a skill published in the GitHub repository Day1Labs/OpenAva (10 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 515 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

oma-translation

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

first-fluke/oh-my-agent · 52 tokens

shogun-readme-sync

A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.

yohey-w/multi-agent-shogun · 66 tokens

review-all

Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.

ncoevoet/claude-review-all · 74 tokens

alibaba-cloud-translation-manager

Manage Alibaba Cloud TongyiTranslate (AnyTrans) via OpenAPI/SDK. Use whenever the user needs translation service resource operations in Alibaba Cloud, including list/create/update actions, task status checks, and troubleshooting AnyTrans API workflows.

rondoflow/rondoflow · 53 tokens

accurate-format-preserving-translation

Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale.

rondoflow/rondoflow · 25 tokens

translation

Translate text between languages. Use when the user asks to translate content, detect language, or work with multilingual text.

fastclaw-ai/fastclaw · 25 tokens