← ClaudeAtlas

globalize-guidelisted

Drive the full internationalization journey for a project — detect the stack, recommend a library, set up the chosen library, wrap existing strings, and connect a translation platform (Globalize.now, default-on). Use when the user asks to add or configure i18n, internationalization, localization, multi-language support, or translations — including when they explicitly mention LinguiJS, Lingui, next-intl, "wrap strings", "find hardcoded text", "make my app translatable", or "set up translations". Triggers on generic phrasings like "add i18n", "internationalize my app", "add translations", "multi-language support", "localize my app", and on library-specific phrasings like "set up Lingui", "set up next-intl", "use Lingui in this project". Does not trigger for unrelated CSS-only RTL questions (those use css-i18n) or for managing an already-set-up Globalize.now project (those use globalize-now-cli-use).
globalize-now/globalize-skills · ★ 3 · Web & Frontend · score 67
Install: claude install-skill globalize-now/globalize-skills
# i18n Orchestrator This skill drives the full i18n journey through five stages: | Stage | Goal | |---|---| | 1 — Inspect and decide | Detect stack, ask all user questions, generate an executable plan | | 1.5 — Globalize account (upfront) | Install CLI + sign in + verify org via `globalize-now-account-setup` | | 2 — Setup | Install + configure the chosen library | | 3 — Convert | Wrap hardcoded strings, extract + compile catalogs | | 4 — Globalize project (end) | Create project + connect repo + set patterns via `globalize-now-project-setup` | Stages 1.5 and 4 only run when the user keeps Globalize connection in scope (default-on; see 1.6). The Globalize work is split deliberately: account creation is interactive and project-independent, so it runs **upfront** while the user is engaged; project + repo setup needs the converted catalog paths, so it runs at the **end**. The orchestrator (this SKILL.md) is library-agnostic. Library- and stack-specific guidance lives in `references/` and is loaded by subagents at dispatch time, driven by `manifest.json`. **Architectural rule:** the orchestrator never executes work directly. It asks Phase 1 questions, generates the plan, dispatches subagents in the background, polls a shared progress workspace at `.globalize/`, and surfaces results. All file modifications, all bash commands, and all reference reading happen inside subagents. **One carve-out:** the interactive Globalize steps (account sign-in in 1.5, project + repo connection i