Dust Translate

OrganizationPopular

dust-tt

dust-translate

Translate or fix Dust product UI and Slack bot translations in the Lingui catalogs (`front/locales/*/**/messages.po`, `sparkle/src/locales/*/messages.po` and `connectors/locales/*/messages.po`). Use after `npm run i18n:extract` leaves empty `msgstr` entries, when `npm run i18n:check` reports missing translations, or when asked to fix a translation.

Overview

Publisher	dust-tt
Repository	`dust`
Skill name	`dust-translate`
Stars	1.5K
Forks	370
Bundled files	1
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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by dust-tt on GitHub. Read the source before you install it.

Installation

Install the Dust Translate 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.
https://github.com/dust-tt/dust/tree/main/.claude/skills/dust-translate
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/dust-tt/dust.git /tmp/dust
mkdir -p .claude/skills
cp -r /tmp/dust/.claude/skills/dust-translate .claude/skills/dust-translate

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

Use it in TypingMind

Enable Dust Translate 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 Dust Translate 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 Dust Translate 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.

Translating the product UI

Catalogs are gettext .po files in front/locales/{locale}/<source directory>/messages.po: every source directory using Lingui has one per entry of CATALOG_LOCALES in front/types/locale.ts. A message used in several directories appears in each of their catalogs; translate it the same way everywhere (npm run i18n:check fails otherwise). When the meanings differ, give the messages a Lingui context in the code instead (see the dust-i18n skill).

The Slack bot has a single catalog per locale, connectors/locales/{locale}/messages.po. Its msgid is the English text itself: keep the Slack mrkdwn (*bold*, _italic_, `code`, <url|label>) around the translated text.

en-US is the source locale: its catalogs are generated and never translated by hand. Every other catalog must have a non-empty msgstr for every message.

Some supported locales reuse another locale's catalog (CATALOG_LOCALE_BY_LOCALE): en-GB renders the en-US messages and only changes date and number formatting. Never create a catalog or write translations for them.

Sparkle components have their own catalogs, one per locale entry of SPARKLE_CATALOG_LOCALES, at sparkle/src/locales/{locale}/messages.po, with the same en-US source-locale rule. Run the commands below from sparkle/ for them. i18n:check does not compare sparkle and front catalogs: translate a message they share (Cancel, Loading) the same way in both by hand.

Procedure

Run npm run i18n:extract from the repository root (or sparkle/) so the catalogs match the code.
For each entry with an empty msgstr:
- Read the #: file reference and the code around the string: know whether it is a button, a title, a description or a toast, and what it refers to.
- Honour the msgctxt line when present (for example verb, button label).
- Translate following the locale style guide and the glossary in references/.
To fix an existing translation, edit its msgstr only. Never edit msgid, msgctxt or the #: references: they are generated from the code.
Run npm run i18n:check from the same directory.

Rules for every locale

Keep placeholders exactly: {name}, {0}, <0>…</0>. You may move them, not rename or drop them. Keep ICU structures ({count, plural, one {…} other {…}}) and translate only the text inside each branch; add the plural categories the target language needs.
Keep keyboard symbols (⌘, ↵, ⇧) and product names from the glossary unchanged.
Match the tone of the English: short, plain, friendly, no marketing language.
Keep the length close to the English: UI labels have little room. Prefer the shorter wording when two are equally correct.
Use sentence case, as in the English source.

Locale style guides

fr-FR: references/fr-FR.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/fr-FR.md6 KB

Frequently asked questions

What does the Dust Translate AI skill do?

Why use Dust Translate on TypingMind?

Because you install it once and use it with any model. Dust Translate 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 Dust Translate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dust-tt/dust/tree/main/.claude/skills/dust-translate. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dust Translate?

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 Dust Translate?

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

Is the Dust Translate AI skill free?

Yes. It is published on GitHub by dust-tt 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

Excalidraw

NousResearch

OrganizationPopular

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

Simple English

Rewrite text to ASD-STE100 Simplified Technical English.

Watchers

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Translating the product UI

Procedure

Rules for every locale

Locale style guides

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now