Translation

Community

kostja94

translation

When the user wants to translate content, create translation workflows, manage terminology, or optimize translation quality. Also use when the user mentions "translate," "translation," "localization copy," "glossary," "terminology," "style guide translation," "machine translation," "human translation," "TMS," or "multilingual content." For strategy, use localization-strategy.

Overview

Publisher	kostja94
Repository	`marketing-skills`
Skill name	`translation`
Stars	979
Forks	137
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by kostja94 on GitHub. Read the source before you install it.

Installation

Install the Translation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kostja94/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/content/translation .claude/skills/translation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Translation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Translation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Translation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Content: Translation

Guides translation workflow, terminology, style, and quality for multilingual content. Covers when to use human vs machine translation, glossary and style guide creation, and SEO considerations. For i18n implementation, hreflang, and URL structure, see localization-strategy.

When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Scope

Workflow: Brief → translate → review
Terminology: Glossary creation and management
Style guide: Voice, tone, formatting per language
Human vs MT: When to use each; post-editing
Quality: QA, consistency, SEO
Market-specific: Terminology by region

Initial Assessment

Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for brand voice, target markets, and product terminology.

Identify:

Content type: Product UI, marketing copy, blog, landing page, docs
Target language(s): Priority locales
Existing assets: Glossary, style guide, translation memory (TM)

1. Translation Workflow

Brief → Translate → Review

Phase	Purpose	Output
Brief	Context, audience, tone, glossary reference, style guide	Translator brief document
Translate	First pass; use glossary + TM when available	Draft translation
Review	Native speaker review; consistency, brand voice, SEO	Final translation

Translator Brief

Include in every project:

Context: What the content is for (landing page, product UI, blog)
Audience: Target market, user persona
Tone: Formal, casual, technical
Glossary: Link or attach; mandatory terms
Style guide: Reference or key rules
Constraints: Character limits (UI), SEO keywords to include naturally

Content-Type Workflow

Content Type	Approach	Notes
Product UI	Glossary-critical; short strings; consistency	Use TM; avoid machine translation
Marketing copy	Brand voice; cultural adaptation	Human translation; see terminology
Blog / Article	SEO; natural keyword placement	Re-research keywords in target language; don't translate keyword lists
Landing page	Conversion-focused; CTA clarity	Human; test localized CTAs
Technical docs	Precision; glossary	TM + glossary; consider MT + post-edit for high volume

2. Glossary & Terminology

Glossary Purpose

Consistency: Same term translated the same way across all content
Brand: Product names, feature names, approved phrasing
Compliance: Safety, legal, regulated terms
Cost: Reduces rework; accelerates review

Glossary Structure

Field	Purpose
Source term	Original (e.g., English)
Target term	Approved translation
Context	Where it appears; usage note
Do not translate	Brand names, product names (when applicable)

Market-Specific Terminology

Term	English	Chinese	Notes
Generative AI	Generative AI, GenAI	AIGC (人工智能生成内容)	Use "AIGC" for China; "Generative AI" for English
Influencer	Influencer	KOL (关键意见领袖)	"KOL" common in Chinese marketing
User	User	用户	Context-dependent
Dashboard	Dashboard	控制台, 仪表盘	Choose one; document in glossary

Principle: Don't translate terminology lists; research how target market searches and speaks. See keyword-research for multi-language keyword research.

3. Style Guide (Translation)

Elements to Define

Element	Purpose
Voice	Brand personality; formal vs casual
Tone	Varies by content type (support = helpful; marketing = persuasive)
Register	Formal (您) vs informal (你) in languages that distinguish
Punctuation	Quotation marks, spacing (e.g., no space before colon in French)
Formatting	Dates, numbers, units; locale-specific
Forbidden	Terms or phrases to avoid

Per-Language Considerations

Chinese: Simplified vs Traditional; measure word usage
German: Formal (Sie) vs informal (du); compound nouns
Japanese: Honorifics; keigo for formal contexts
Arabic: RTL; formal vs dialect

4. Human vs Machine Translation

When to Use Human Translation

Scenario	Reason
Product UI	Terminology, UX clarity, brand
Marketing copy	Persuasion, cultural nuance, CTAs
Landing pages	Conversion; tested copy
Legal, compliance	Accuracy, liability
Brand-critical	Taglines, campaign copy

When Machine Translation (MT) May Be Acceptable

Scenario	Condition
High-volume, low-stakes	Internal docs, user-generated content
Draft / triage	MT + human post-edit (MTPE)
Real-time	Chat, support; with disclaimer

Avoid

Raw MT for product/marketing: Terminology errors, cultural misfires, poor SEO
MT without post-edit for customer-facing content
Translating keyword lists instead of re-researching in target language

5. Translation Memory (TM) & TMS

Translation Memory

What: Stores approved source↔target sentence pairs
Benefit: Consistency; reuse; lower cost per word; faster turnaround
Best practice: Maintain TM; clean duplicates; align with glossary

Translation Management System (TMS)

Use for: Centralized workflow; glossary + TM integration; vendor management
When: Multiple languages; ongoing translation; team collaboration

6. Quality & SEO

Quality Checklist

SEO for Translated Content

Keywords: Re-research in target language; don't translate from source
Metadata: Title, description translated; see title-tag, meta-description
Hreflang: Technical implementation in localization-strategy; translation produces the content
Thin content: Avoid publishing many low-quality translated pages at once; can trigger penalties. See localization-strategy Multilingual Risks.

7. Integration with Localization

Topic	Skill
i18n implementation	localization-strategy
URL structure, hreflang	localization-strategy
Translation workflow, glossary, style	This skill (translation)
Keyword research by market	keyword-research; localization-strategy

When adding a new locale: create glossary, style guide, then translate. See localization-strategy for technical checklist (hreflang, sitemap, metadata).

Output Format

Translator brief (context, audience, glossary, style)
Glossary additions or updates
Style guide notes for target language
Human vs MT recommendation
Quality checklist

Related Skills

Strategy & Technical

localization-strategy: i18n, hreflang, URL structure, pricing by market; translation produces content for localized pages
content-strategy: Multilingual content planning; avoid thin translations
content-marketing: Content types and formats; translation as one channel adaptation

SEO & Content

keyword-research: Multi-language keyword research; don't translate keyword lists
page-metadata: Hreflang implementation
title-tag, meta-description: Translate metadata per locale
copywriting: Source copy to translate; brand voice
image-optimization: Localize image filenames for translated pages

Frequently asked questions

What does the Translation AI skill do?

Why use Translation on TypingMind?

Because you install it once and use it with any model. Translation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Translation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kostja94/marketing-skills/tree/main/skills/content/translation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Translation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Translation?

As many as you like. As long as a model supports skills, you can use Translation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Translation AI skill free?

Yes. It is published on GitHub by kostja94 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Image To Code

Leonxlnx

CommunityPopular

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as…

Consulting Analysis

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis,…

Github Deep Research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces…

Changelog Generator

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns…

Translation

Overview