bilingual
Use when you need to translate marketing copy between EN and zh-TW while preserving brand voice, tone, and impact. Not word-level translation — a voice-preserving rewrite in the target locale.
npx skills add hogan-tech/brand-loom --skill bilingual --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Bilingual Translator (EN ↔ zh-TW) Voice-preserving translation between English and Traditional Chinese. Preserves brand tone, audience targeting, and phrase preferences across languages. ## Quick start - CLI: `brand-loom run bilingual --text "Ship it, then iterate." --target-locale zh-TW` - Python API: `run_skill("bilingual", "Ship it.", target_locale="zh-TW")` ## Features - Voice-preserving rewrite (not word-level translation) - Supports `preserve_terms` to keep brand names, acronyms verbatim - Full `brand_context` support (tone, audience, do/avoid phrases) - Returns unchanged if source = target locale > **Multi-language support beyond EN/zh-TW** (auto-detection, 10+ locales, continuous voice alignment) lives in hosted **[Neoxra](https://neoxra.com)**.
- Quick start
- Features
What does the bilingual skill do?
Use when you need to translate marketing copy between EN and zh-TW while preserving brand voice, tone, and impact. Not word-level translation — a voice-preserving rewrite in the target locale.
How do I install it?
Run `npx skills add hogan-tech/brand-loom --skill bilingual --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From hogan-tech/brand-loom, a repository with 17 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.