localize — community localize, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Internationalization Agents automating the extraction and replacement of hardcoded strings in codebases. ryOS, made with Cursor

ryokun6 ryokun6
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The localize skill by ryokun6 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for Internationalization Agents automating the extraction and replacement of hardcoded strings in codebases.

Core Value

Empowers agents to systematically extract hardcoded strings using Bun scripts and replace them with t() function calls. Provides automated translation synchronization across multiple language files and machine translation capabilities for [TODO] keys, streamlining the localization workflow.

↓ Capabilities Granted for localize

Extracting hardcoded strings from source files using pattern matching
Replacing strings with t() calls across components
Synchronizing translations across multiple language files
Machine translating incomplete keys marked as [TODO]
Validating translation coverage in JSON files

! Prerequisites & Limits

  • Requires Bun runtime environment for script execution
  • Depends on existing t() function implementation in codebase
  • Pattern matching parameter needed for string extraction
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

localize

Install localize, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Localize App or Component

Workflow Checklist

- [ ] 1. Extract hardcoded strings
- [ ] 2. Replace with t() calls in source files
- [ ] 3. Add English translations to en/translation.json
- [ ] 4. Sync translations across languages
- [ ] 5. Machine translate [TODO] keys
- [ ] 6. Validate coverage

Step 1: Extract Hardcoded Strings

bash
1bun run scripts/extract-strings.ts --pattern [PATTERN]

Step 2: Replace Strings with t() Calls

For each component:

  1. Add import: import { useTranslation } from "react-i18next";
  2. Add hook: const { t } = useTranslation();
  3. Replace strings: t("apps.[appName].category.key")
  4. Add t to dependency arrays for useMemo/useCallback

Key Structure

apps.[appName].menu.*        # Menu labels
apps.[appName].dialogs.*     # Dialog titles/descriptions
apps.[appName].status.*      # Status messages
apps.[appName].ariaLabels.*  # Accessibility labels
apps.[appName].help.*        # Help items (auto-translated)

Common Patterns

tsx
1// Basic
2t("apps.ipod.menu.file")
3
4// With variables
5t("apps.ipod.status.trackCount", { count: 5 })
6
7// Conditional
8isPlaying ? t("pause") : t("play")
9
10// With symbol prefix
11`✓ ${t("apps.ipod.menu.shuffle")}`

Step 3: Add English Translations

Add to src/lib/locales/en/translation.json:

json
1{
2  "apps": {
3    "ipod": {
4      "menu": { "file": "File", "addSong": "Add Song..." },
5      "dialogs": { "clearLibraryTitle": "Clear Library" },
6      "status": { "shuffleOn": "Shuffle ON" }
7    }
8  }
9}

Step 4: Sync Across Languages

bash
1bun run scripts/sync-translations.ts --mark-untranslated

Adds missing keys to all language files, marked with [TODO].

Step 5: Machine Translate

bash
1bun run scripts/machine-translate.ts

Requires GOOGLE_GENERATIVE_AI_API_KEY env variable.

Step 6: Validate

bash
1bun run scripts/find-untranslated-strings.ts

Component Guidelines

ComponentWhat to translate
Menu barsAll labels, items, submenus
DialogsTitles, descriptions, button labels
StatusshowStatus() calls, toasts
Help itemsAuto-translated via useTranslatedHelpItems

Notes

  • Emoji/symbols (♪, ✓) can stay hardcoded
  • Help items use pattern: apps.[appName].help.[key].title/description
  • Include t in dependency arrays when used in useMemo/useCallback

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is localize?

Ideal for Internationalization Agents automating the extraction and replacement of hardcoded strings in codebases. ryOS, made with Cursor

How do I install localize?

Run the command: npx killer-skills add ryokun6/ryos/localize. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for localize?

Key use cases include: Extracting hardcoded strings from source files using pattern matching, Replacing strings with t() calls across components, Synchronizing translations across multiple language files, Machine translating incomplete keys marked as [TODO], Validating translation coverage in JSON files.

Which IDEs are compatible with localize?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for localize?

Requires Bun runtime environment for script execution. Depends on existing t() function implementation in codebase. Pattern matching parameter needed for string extraction.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add ryokun6/ryos/localize. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use localize immediately in the current project.

Related Skills

Looking for an alternative to localize or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI