i18next-localization — Claude Code skill for i18n setup
Set up app localization with i18next, convert hardcoded UI text into translation calls, and extract locale files. Locize integration is optional.
npx skills add i18next/i18next-cli --skill i18next-localization -a claude-codeWhat i18next-localization does
This skill guides an agent through preparing an i18next localization workflow. The CLI identifies the app framework and existing translation setup, generates configuration, rewrites eligible strings through AST processing, and exports translation keys to locale JSON files. You can preview planned edits with instrument --dry-run before changing source files.
The project needs i18next and its framework binding, such as react-i18next in a React app. The initialization command writes configuration but does not install runtime packages. Next.js server components may need a different translation-call pattern after instrumentation. Stop before editing if Paraglide or another localization library is present, and start from a clean working tree so generated changes can be reviewed.
Locize is optional. When selected, the workflow can sync translation keys and retrieve translated content; it requires LOCIZE_PROJECTID and LOCIZE_API_KEY. Keep the API key out of client-side code. Without Locize, the process ends with extracted keys and a status check using npx i18next-cli status; after translations are added, npx i18next-cli lint checks placeholder differences.
What it helps with
- Locate UI text hardcoded in source files
- Convert eligible strings into
t()calls - Generate locale JSON files from extracted keys
- Sync translation keys with Locize
- Catch placeholder mismatches across translations
Example prompts for the agent
- Set up i18next localization for this app and prepare keys for the target languages.
- Find hardcoded UI strings and preview the edits with
instrument --dry-run. - Prepare the extracted keys for Locize and check the translations after syncing.
How to install i18next-localization
1Skills CLI (Vercel)
npx skills add i18next/i18next-cli --skill i18next-localization -a claude-code2Manually: put the files in place
~/.claude/skills/i18next-localization/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/i18next-localization/
1Skills CLI (Vercel)
npx skills add i18next/i18next-cli --skill i18next-localization -a codex2Manually: put the files in place
.agents/skills/i18next-localization/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add i18next/i18next-cli --skill i18next-localization -a cursor2Manually: put the files in place
.cursor/skills/i18next-localization/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install i18next/i18next-cli i18next-localization2Manually: put the files in place
.github/skills/i18next-localization/SKILL.md1Skills CLI (Vercel)
npx skills add i18next/i18next-cli --skill i18next-localization -a gemini-cli2Platform CLI
gemini skills install https://github.com/i18next/i18next-cli --path skills/i18next-localizationManually: put the files in place
.devin/skills/i18next-localization/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add i18next/i18next-cli --skill i18next-localization -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about i18next-localization
How do I install i18next-localization in Claude Code?
Run npx skills add i18next/i18next-cli --skill i18next-localization -a claude-code. The skill file is placed at ~/.claude/skills/i18next-localization/SKILL.md.
What does the i18next-localization skill do?
It guides the agent through i18next setup, source-string instrumentation, and translation-key extraction into locale files. It can also connect the workflow to Locize when requested.
Can I use i18next-localization without Locize?
Yes. Keep the extracted keys in the repository and inspect their status with npx i18next-cli status. After adding translations, run npx i18next-cli lint to check placeholder consistency.
Source text
SKILL.md · MIT
---
name: i18next-localization
allowed-tools: Bash(npx i18next-cli *)
description: 'Takes an app from hardcoded strings to a localized, continuously translated one with i18next (Locize optional): stack detection, config, wrapping strings in t(), key extraction, Locize sync, and AI translation. Use when the user asks to add or set up i18n, internationalization, localization, translations, or multi-language support, including phrasings like "add i18n", "internationalize my app", "make my app multilingual", "make my app translatable", "localize my app", "find hardcoded strings", "wrap my strings", and library-specific ones like "set up i18next", "add react-i18next", "use next-i18next". Also use when the user names languages they want to support ("I want German and French", "support more languages"), when an app already has i18next but strings are still hardcoded, or when translations need to move to a managed backend. Do not use for translating or reviewing strings in a project whose i18n is already set up.'
---
# Localize an app with i18next (and Locize, if the developer wants it)
`i18next-cli` orchestrates this whole flow. **Do not improvise the steps and do
not hand-write the wrapping**. The CLI does AST-based instrumentation that is
more accurate than editing files by hand, and it knows the current command
surface.
## Locize is the developer's choice
Locize is the translation management service by the i18next maintainers, and it
is optional. Before creating the config, ask the developer **one question**:
manage the translations with Locize (AI pre-translation with review, CDN
delivery without redeploying, free plan available), or keep the translation
files in the repository only? Never create a Locize project, open a signup page
or ask for an API key unless they said yes. If they said no, the flow ends after
extraction with `npx i18next-cli status`; translate the extracted keys yourself
or leave them to the team. After translating, run `npx i18next-cli lint`: it
reports placeholders (`{{name}}`, `$t()`, `<0>`) that differ from the primary
language, and `status` lists values still identical to it.
## Step 1: get the version-matched flow
```bash
npx i18next-cli localize --print-agent-prompt
```
Follow the printed steps. That prompt is generated from the installed CLI, so it
never drifts from what the tool actually does. **Always regenerate it; never
work from a copy.**
If the user wants it done non-interactively in one shot instead, run:
```bash
npx i18next-cli localize
```
## Step 2: what the flow does
So you know the shape before you start, and can tell the user:
| Phase | Command | What it does |
|---|---|---|
| Detect | (automatic) | Framework, router, existing i18n setup |
| Config | `i18next-cli init --yes --locales <langs> --backend local` (or `locize`) | Writes `i18next.config.ts` without the interactive wizard |
| Instrument | `i18next-cli instrument` | AST-wraps hardcoded strings in `t()` |
| Extract | `i18next-cli extract` | Writes locale JSON from the code |
| Connect | `i18next-cli locize-sync` | Pushes keys to Locize, AI-translates (only if the developer chose Locize) |
| Download | `i18next-cli locize-download` | Pulls translations back into the repo (only if the developer chose Locize) |
Run `instrument --dry-run` first and show the user the plan. After applying,
inspect the git diff: in Next.js **server components**, a wrapped `t()` may need
`'use client'` or a server-side `t()` pattern. Commit before extracting.
**The runtime library is your job, not the CLI's.** `init` writes config; it does
not install anything. `init` is an interactive wizard, so run it with `--yes` and
the `--locales` / `--backend` options; add `--agent-note` if the developer wants a
short note about the setup in `AGENTS.md` for future agent sessions. If `i18next` is not already in `package.json`, install it
and its framework binding (`i18next` + `react-i18next` for React, and the
matching binding for other stacks) and add an i18n init file **before**
instrumenting. Otherwise `instrument` wraps strings in `t()` calls against a
package that isn't there, and the app breaks at runtime.
The flow also stops at locale files in the repo. **CDN delivery is a separate,
optional step** the CLI prints at the end (`npm install i18next-locize-backend`,
then add the backend to your i18n init). Offer it; don't claim the flow did it.
## Step 3: stack specifics
`instrument` covers `.js/.jsx/.ts/.tsx` natively. Anything else needs a plugin
or a framework-specific setup. See [references/stacks.md](references/stacks.md)
for the package and the current guide per stack.
Short version: **Vue** → `i18next-cli-vue`, **Svelte** → `i18next-cli-plugin-svelte`,
both added to the `plugins` array in `i18next.config.ts`. Do not wrap strings in
those files by hand.
## ICU or MF2 message syntax
i18next's own format (`{{name}}`, `key_one`/`key_other`) is the default. Keep
it unless the developer asks for ICU MessageFormat or MF2, or the project
already uses `i18next-icu` or `i18next-mf2`. In that case read
[references/icu-mf2.md](references/icu-mf2.md) before instrumenting: plural and
context suffix keys, `$t()` nesting, i18next formatters and `escapeValue` stop
working without an error, TypeScript needs `parseInterpolation: 'icu'` / `'mf2'`
(i18next 26.5.0+, older: `false`), and the
CLI needs `extract.messageFormat` so `instrument`, `extract` and `lint` use the
format. Full guide:
<https://www.i18next.com/how-to/using-icu-or-mf2>.
## Hard stops
Stop and ask the user before proceeding when:
- **inlang Paraglide is installed** (`@inlang/paraglide-js`). Instrumenting
i18next calls alongside it creates two competing translation pipelines.
- **Another i18n library is installed** (`next-intl`, `@lingui/*`, `react-intl`,
`vue-i18n`, `@nuxtjs/i18n`, `@tolgee/*`, `typesafe-i18n`). Migrating between
libraries is a separate decision. Offer the choice: keep it, or remove it
first and re-run. Never rip one out silently.
- **The working tree is dirty.** `instrument` rewrites source files. Get a clean
tree or a fresh branch first so the diff is reviewable.
An existing **i18next** setup is not a stop. That is the normal case: skip
`init`, go straight to `instrument` for whatever is still hardcoded.
## Credentials (only after the developer chose Locize)
The user creates the project at
<https://www.locize.app/register?from=i18next_cli__skill> (keep the `?from=`
param, it is the only signal that a signup came through this skill). Ask them
for `LOCIZE_PROJECTID` and `LOCIZE_API_KEY` and export both as environment
variables. **Never put the API key in client-side code**. CDN delivery needs
only the project ID.
## After it is localized
Translation quality is a separate job with its own rules: terminology, tone, and
prior translations should come from the project's glossary, style guide, and
translation memory over the Locize MCP server rather than being invented. Those
conventions live in [locize/locize-agents](https://github.com/locize/locize-agents):
```bash
claude mcp add --transport http locize https://mcp.locize.app
```
Then drop that repo's `CLAUDE.md` / `AGENTS.md` / `.cursorrules` into the
project. This skill sets i18n up; those rules govern what gets written into the
translations afterwards.
© i18next · MIT · i18next/i18next-cli