Agent skill

I18n Studio

by glebis in glebis/claude-skills

This skill should be used when editing, translating, or reviewing an Astro-style i18n string corpus (files of the form export default { en: {...}, ru: {...} } under src/i18n/strings), or when the…

MITAuto-check passedFrontend & Design

Install I18n Studio

skills CLI
$ npx skills add glebis/claude-skills --skill i18n-studio -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install glebis/claude-skills i18n-studio --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/i18n-studio .claude/skills/i18n-studio && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
i18n-studio
GitHub stars
390
Token cost
~1.9k tokens
SKILL.md length
833 words
Files
3 (incl. scripts, references)
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when editing, translating, or reviewing an Astro-style i18n string corpus (files of the form export default { en: {...}, ru: {...} } under src/i18n/strings), or when the…

  • Wants to fill in missing translations
  • SKILL.md covers Purpose, When to use, Locate the strings directory… and Start the server (required for…, plus 3 more sections
  • Runs JavaScript scripts from its folder; calls node and npm
  • Accept/review translations

What it does

I18n Studio is an agent skill from glebis/claude-skills. This skill should be used when editing, translating, or reviewing an Astro-style i18n string corpus (files of the form export default { en: {...}, ru: {...} } under src/i18n/strings), or when the user wants to fill in missing translations, audit coverage, accept/review translations, propagate an edit across duplicate strings, get translation candidates, bulk-edit UI microcopy, or open a visual/keyboard translation editor. Drives the standalone i18n Studio tool at ~/aiprojects/i18n-studio (AST-safe minimal-diff…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/api.md`).

It sits in Frontend & Design, covering Translation and Internationalization. It works with Astro. The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

  • Wants to fill in missing translations
  • Accept/review translations
  • Propagate an edit across duplicate strings
  • Get translation candidates

Example prompts

  • “/i18n-studio”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 3b88261. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

I18n Studio loads about 1.9k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 161 tokens; SKILL.md has 833 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from glebis/claude-skills at commit 3b88261, republished under its MIT licence (© glebis). 833 words, ~1,859 tokens.

Download SKILL.mdSave it as .claude/skills/i18n-studio/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
i18n-studio
description
This skill should be used when editing, translating, or reviewing an Astro-style i18n string corpus (files of the form export default { en: {...}, ru: {...} } under src/i18n/strings), or when the user wants to fill in missing translations, audit coverage, accept/review translations, propagate an edit across duplicate strings, get translation candidates, bulk-edit UI microcopy, or open a visual/keyboard translation editor. Drives the standalone i18n Studio tool at ~/ai_projects/i18n-studio (AST-safe minimal-diff saves via ts-morph, acceptance review state, duplicate propagation, hot-reload, and Claude translation suggestions).

i18n Studio

Purpose

i18n Studio edits Astro-style i18n string files safely: files shaped like export default { en: {...}, ru: {...} } where leaves are UI strings. It writes one string literal at a time through a ts-morph AST, so every save is a minimal one-line diff with all surrounding formatting preserved, and a running dev server hot-reloads. It also produces Claude translation candidates that preserve HTML tags and tone.

Use it instead of hand-editing .ts string files with Edit/sed: manual edits risk formatting churn, broken quoting/escaping, and desynced languages. The AST layer avoids all three.

When to use

  • Filling in missing translations for a language (e.g. "translate the new hero copy to Russian", "fill the German gaps").
  • Auditing coverage ("which strings are untranslated?").
  • Editing UI microcopy in one or more languages.
  • Getting translation candidates for a specific string.
  • Opening a visual editor for a human to translate interactively ("open the translation editor").

Applies to any repo whose translations follow the export default { <lang>: {...} } convention, not one specific project.

Locate the strings directory first

The tool defaults to <cwd>/src/i18n/strings. Confirm the real location before starting (it may differ):

bash
ls src/i18n/strings 2>/dev/null || find . -path '*/i18n/strings' -type d -not -path '*/node_modules/*' | head

Use that path as --dir below. Ensure the tool is installed once: cd ~/ai_projects/i18n-studio && npm install.

Start the server (required for the API and the UI)

Start it in the background, pointed at the target strings dir, and wait until it is reachable:

bash
node ~/ai_projects/i18n-studio/server.mjs --dir "$PWD/src/i18n/strings" --port 4331 &
until curl -sf http://localhost:4331/api/strings >/dev/null; do sleep 0.5; done

Pass --langs en,ru,de if the corpus has languages beyond the en,ru default, and --voice "<one-line tone brief>" to steer suggestion style. Stop it with kill %1 (or the printed PID) when finished.

For a human to edit visually, start the server the same way and share the URL (http://localhost:4331); do not try to click the web UI programmatically.

Drive it with the helper CLI

scripts/i18n.mjs (dependency-free, Node 18+) wraps the API. Point it at the server with I18N_URL if the port is not 4331.

bash
S=~/ai_projects/claude-skills/i18n-studio/scripts/i18n.mjs

node "$S" audit --to ru                          # status breakdown + untranslated/missing
node "$S" audit --to ru --pending                # also list translated-but-unaccepted
node "$S" get     Hero.ts en h1                   # read a value
node "$S" suggest Hero.ts h1 --from en --to ru    # 3 candidates (proposals only)
node "$S" set     Hero.ts ru h1 "Сначала — результат"  # AST-safe write (→ pending)
node "$S" accept  Hero.ts ru h1                   # mark reviewed/accepted
node "$S" unaccept Hero.ts ru h1                  # back to pending
node "$S" ignore  Dream.ts ru s2                  # mark n/a — "doesn't need translation"
node "$S" unignore Dream.ts ru s2                 # back to untranslated/pending

Typical translation-fill loop: audit --to <lang> to see the breakdown and gaps → for each gap, suggest from the source language → review the candidate (see rules below) → set the chosen value → accept once it is right.

Acceptance is a durable review state (sidecar .i18n-status.json); editing a value automatically drops it back to pending. A cell can instead be marked n/a ("doesn't need translation" — a name, a fragment, a shared token): ignore drops it out of the untranslated/pending gap counts so it stops nagging, and — unlike accept — works on an empty/untranslated cell. Like acceptance it is value-coupled, so translating the cell later re-surfaces it. For a human reviewer, the fullscreen review mode (below) is faster than the CLI.

The raw routes (GET /api/strings, POST /api/save, POST /api/suggest), data shapes, dot-path rules, config flags, and a no-server library path are documented in references/api.md. Read it before doing anything beyond the CLI above.

Show full SKILL.md (373 more words)Show less

Visual editor: review mode, filters, duplicates

For a human, the browser UI is the fast path. Start the server, share the URL, and point out:

  • Source → target switch in the header (work any language against any reference).
  • Filters: show all / untranslated / pending / accepted / n/a / duplicates / code-like, by file, with sort (file / path / status / duplicates-first) and live counts.
  • Hide code-like: asset paths, CSS vars/colors, class names and identifiers are detected and hidden from the queue by default (they rarely need translation).
  • Accept and n/a buttons per row (and a duplicates badge ×N). The n/a toggle marks a string as not needing translation — it works even on empty cells and removes them from the untranslated queue.
  • Duplicate propagation: after editing a string that others shared, a banner offers apply to all — one click updates every entry that held the old value.
  • Fullscreen review (review ▸): steps through the filtered set one at a time, fully keyboard driven with a visible legend — ←/→ or j/k move, a accept & next, p pending, i mark n/a & next, e edit, s suggest, 1/2/3 apply a suggestion, u undo, Esc close, > focus. Tab lands on the edit field; clicking the file name filters the list to that file. This is the tool for grinding through thousands.
  • Focus mode (Shift + .): hides all chrome, leaving only the strings.

Rules that matter

  • Never blindly apply a suggestion. Before set, verify the candidate keeps the same HTML tags and entities as the source (<b>, <span ...>, &nbsp;, &#39;, &mdash;) in the same positions, and does not translate code identifiers or proper nouns. Suggestions are proposals, not decisions.
  • Interpolated strings are editable, placeholders are sacred. Template literals with ${...} come back editable: true, interp: true (badged ${…}); translate the prose but keep every ${...} placeholder exactly. Only non-string leaves (numbers, identifiers) stay read-only and must be edited in the .ts source.
  • Dot-paths use numeric indices for arrays, e.g. weeks.2.sessions.1.t.
  • One save writes one leaf. Loop for bulk work; there is no batch write.
  • Hot reload needs the target project's own dev server running; the write lands on disk either way.
  • Confirm before mass edits. Auto-translating a whole language is a large, outward-facing change to the product copy; surface the gap list and confirm scope with the user before writing many strings.

© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in i18n-studio of glebis/claude-skills.

  • SKILL.md
  • references/api.md
  • scripts/i18n.mjs

Open the folder on GitHubat commit 3b88261

Compare with similar skills

I18n Studio next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

I18n Studio compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
I18n Studio this skillglebis/claude-skills390—~1.9kAutomated safety check: PassMIT
Chatbox i18n Translatorchatboxai/chatbox42k—~508Automated safety check: PassGPL-3.0
Internationalization Workflow with i18niOfficeAI/AionUi33k1 repos~1.9kAutomated safety check: PassApache-2.0
Enforce Rules For I18nmoeru-ai/airi50k—~1.5kAutomated safety check: PassMIT
Claude Desktop Chinese Localizationjavaht/claude-desktop-zh-cn7.5k—~1.6kAutomated safety check: PassMIT
Translation ReviewDevolutions/UniGetUI26k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Chatbox i18n Translator

    chatboxai/chatbox

    Translates new or changed i18n keys from a Chatbox Pro diff, staged changes or a commit range, writing the locale JSON files directly with a built-in glossary.

    42k GitHub stars~508 tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed
  • Standards for keeping all user-facing text translatable: read the i18n config first, use namespaced keys, reuse shared strings and follow the key naming rules.

    33k GitHub starsUsed in 1 repo~1.9k tokens
    Frontend & DesignAuto-check passed
  • Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Claude Desktop Chinese Localization

    javaht/claude-desktop-zh-cn

    Adds missing Simplified and Traditional Chinese translations to the Claude Desktop Chinese patch across three layers, then checks how many mappings actually hit.

    7.5k GitHub stars~1.6k tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Translation Review

    Devolutions/UniGetUI

    Reviews UniGetUI .json language files for localization quality, detects parity issues, English-equal entries, wrong-script content, and cross-language outliers, then generates a dataset for…

    26k GitHub stars~1.3k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Frontend I18n

    langflow-ai/langflow

    Add, change, or review user-facing text in the Langflow frontend using the i18n system (i18next / react-i18next).

    155k GitHub stars~1k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from glebis/claude-skills

All 92 skills in this repo
  • Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.

    390 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.

    390 GitHub stars~973 tokensUpdated yesterday
    Auto-check passed
  • Deep Research

    glebis/claude-skills

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.

    390 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes
  • Elimination Research

    glebis/claude-skills

    This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

    390 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Narrated HTML Presentations

    glebis/claude-skills

    Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.

    390 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check: notes
  • Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

    390 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about I18n Studio

What does I18n Studio do?

This skill should be used when editing, translating, or reviewing an Astro-style i18n string corpus (files of the form export default { en: {...}, ru: {...} } under src/i18n/strings), or when the…. I18n Studio is an agent skill from glebis/claude-skills.} } under src/i18n/strings), or when the user wants to fill in missing translations, audit coverage, accept/review translations, propagate an edit across duplicate strings, get translation candidates, bulk-edit UI microcopy, or open a visual/keyboard translation editor.

When should I use I18n Studio?

I18n Studio fits situations like: wants to fill in missing translations; accept/review translations; propagate an edit across duplicate strings; get translation candidates.

How do I install I18n Studio in Claude Code?

Run `npx skills add glebis/claude-skills --skill i18n-studio -a claude-code`. Or copy the skill folder (i18n-studio in glebis/claude-skills) into .claude/skills/i18n-studio in your project. Claude Code loads it when a task matches its description.

How do I install I18n Studio in Codex?

Run `npx skills add glebis/claude-skills --skill i18n-studio -a codex`. Or copy the skill folder (i18n-studio in glebis/claude-skills) into .agents/skills/i18n-studio in your project. Codex loads it when a task matches its description.

Can I use I18n Studio in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glebis/claude-skills --skill i18n-studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/i18n-studio, .gemini/skills/i18n-studio, .github/skills/i18n-studio and .opencode/skills/i18n-studio in your project.

What does I18n Studio need to run?

Going by SKILL.md and its folder, I18n Studio needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npm). Our summary lists: Node.js.

Does I18n Studio access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is I18n Studio safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does I18n Studio use?

I18n Studio is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does I18n Studio use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to I18n Studio?

Skills that share tags, products or a category with I18n Studio: Chatbox i18n Translator (chatboxai/chatbox, 42k stars), Internationalization Workflow with i18n (iOfficeAI/AionUi, 33k stars), Enforce Rules For I18n (moeru-ai/airi, 50k stars) and Claude Desktop Chinese Localization (javaht/claude-desktop-zh-cn, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains I18n Studio?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 390 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 8, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.