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 written-hokkiengit 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/written-hokkien)<a href="https://agentmods.dev/skills/tzengyuxio/skills/written-hokkien"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/written-hokkien/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/written-hokkien"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/written-hokkien.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00250 | $0.06337 |
| Opus 5 | $0.00125 | $0.03168 |
| Sonnet 5 | $0.00050 | $0.01267 |
| Haiku 4.5 | $0.00025 | $0.00634 |
Grade A, and why
written-hokkien 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Written Hokkien — 台語 / 閩南語 / 台文書面化
Transform text into written Taiwanese Hokkien （台語 / 閩南語 / 台灣閩南語） — the written representation of a Sinitic language with around 1700 years of history, spoken today by tens of millions across Taiwan and Southeast Asia. The result should read like a 台文 short story, a 漢羅 poem by 陳明仁 or 李勤岸， a column in 《台文通訊 BONG 報》, or a 教育部 textbook for 本土語言課程 — fluent in Taiwanese syntax and faithful to one of the two standard orthographies.
This skill covers two intensities, distinguished primarily by the writing system rather than by syntactic depth:
- Light = pure Hanzi （純漢字） — the entire text in 漢字， drawing on the 教育部 700-字詞推薦用字 plus 訓用字. Suitable for textbooks, newspapers, and general readers who prefer Han characters throughout.
- Heavy = Han-Roman mixed script （漢羅混寫） — 本字 stay in 漢字， but function words and lexemes that resist standard Hanzi (such as ê, beh, kah, siánn, leh) are written in 台羅 (the 教育部 臺灣台語羅馬字拼音方案， 2006). This is the preferred form in much contemporary 台文文學（賴和、鄭清文、陳明仁《路樹下 ê tó͘-peh-á》, 李勤岸 詩集，胡長松， 陳雷）.
In both intensities the syntax must be Taiwanese, not transliterated Mandarin. A sentence like 「我有去過日本」 is Taiwan Mandarin, not 台文； the 台文 form is 「我有去過日本 ah」(Heavy) or 「我有去過日本矣」(Light).
Background — Orthographic history
- 白話字 (POJ, Pe̍h-ōe-jī) — Romanized 閩南語 introduced by Presbyterian missionaries in the 1830s; 巴克禮 (Thomas Barclay) completed the first POJ New Testament around 1873 (revised 1916). POJ remained the dominant Taiwanese script for church communities for over a century.
- 台羅 (Tâi-lô) — The 教育部 臺灣閩南語羅馬字拼音方案， promulgated 2006-10-14, integrating POJ and TLPA conventions. Today 台羅 is the standard taught in 本土語言課程 and used in 教育部《臺灣台語常用詞辭典》.
- 教育部推薦用字 — Two waves (2007 / 2008, 2009 revision) totalling 700 字詞 of recommended Hanzi, classified into 本字 (etymological), 訓用字 (semantic borrowing), and 新造字（新造）. For Heavy mode, words still lacking a settled Hanzi (notably ê, beh, kah, leh, siánn-mih variants) are written in 台羅.
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 · 446 lines · 250 tokens per session scan A b239a0a70516
written-hokkien is a skill published in the GitHub repository tzengyuxio/skills (46 stars, last pushed 2mo ago), licensed MIT. It adds 250 tokens to every session and 6,337 once invoked, about $0.0013 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.