Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tzengyuxio/skills --skill taiwan-mandaringit clone --depth 1 https://github.com/tzengyuxio/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tzengyuxio/skills/taiwan-mandarin)<a href="https://agentmods.dev/skills/tzengyuxio/skills/taiwan-mandarin"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/taiwan-mandarin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tzengyuxio/skills/taiwan-mandarin"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/taiwan-mandarin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00206 | $0.06336 |
| Opus 5 | $0.00103 | $0.03168 |
| Sonnet 5 | $0.00041 | $0.01267 |
| Haiku 4.5 | $0.00021 | $0.00634 |
Grade A, and why
taiwan-mandarin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taiwan Mandarin — 台灣國語
Transform text into Taiwan Mandarin (台灣國語) — a living sociolect of Mandarin shaped by decades of contact with Taiwanese Hokkien. The result should read like an authentic Taiwanese speaker typing casually on LINE, PTT, or 無名小站 — warm, colloquial, and unmistakably local.
Taiwan Mandarin is NOT broken Mandarin or a caricature. It is a systematic variety with its own phonology (often reflected in spelling), lexicon, and pragmatic particle system. Every feature reflects real contact patterns between Mandarin and Taiwanese Hokkien, sometimes layered with Japanese loanwords and BBS-era internet culture.
This skill targets the written representation of Taiwan Mandarin — not the oral phonetics, but the ways those phonetic and lexical features surface in casual text.
Arguments
$0— (Optional) Path to a markdown or text file. If omitted, ask for inline text or find the most recent text in conversation context.
Step 1: Load the Text
- If
$0is provided, read the file. - If no argument, find the most recent text in the conversation, or ask the user.
- The input can be Mandarin Chinese (rewrite as Taiwan Mandarin), any language (translate to Taiwan Mandarin), or English (translate to Taiwan Mandarin).
Step 2: Apply Taiwan Mandarin Patterns
Apply the rules below systematically. The goal: every 2-3 sentences should carry at least one marker from particles, vocabulary, or spelling. Not every rule applies to every sentence — pick the ones that fit naturally.
Taiwan Mandarin exists on a continuum. This skill targets the light-to-heavy colloquial range — from a young Taiwanese texting a friend, up to 2000s BBS netizen style. It deliberately excludes caricature (e.g., 鄉土劇 exaggeration).
Grammar Patterns（語法模式）
G1. 「有」+ 動詞 — 完成/經驗體 [Hard, Light+]
Taiwanese Hokkien uses 有 + verb to mark completion or experience. This transfers into Taiwan Mandarin, replacing the standard 了/過 in many casual contexts.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 600 lines · 206 tokens per session scan A 7d7695d379a0
taiwan-mandarin is a skill published in the GitHub repository tzengyuxio/skills (46 stars, last pushed 2mo ago), licensed MIT. It adds 206 tokens to every session and 6,336 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.