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 lanamaysu/agent-skills --skill zh-tw-writinggit clone --depth 1 https://github.com/lanamaysu/agent-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/lanamaysu/agent-skills/zh-tw-writing)<a href="https://agentmods.dev/skills/lanamaysu/agent-skills/zh-tw-writing"><img src="https://agentmods.dev/badge/skills/lanamaysu/agent-skills/zh-tw-writing/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/lanamaysu/agent-skills/zh-tw-writing"><img src="https://agentmods.dev/badge/skills/lanamaysu/agent-skills/zh-tw-writing.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 | $0.00212 | $0.03757 |
| Opus 5.5 | $0.00085 | $0.01503 |
| Sonnet 5.5 | $0.00042 | $0.00751 |
| Haiku 4.5 | $0.00021 | $0.00376 |
Grade A, and why
zh-tw-writing 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zh-tw-writing
TL;DR
- 必用台灣術語：元件、非同步、資料、伺服器、資料庫、快取；框架與程式碼維持英文。
- 絕對禁用：組件/组件、異步/异步、數據/数据、服務器/服务器、函數/函数、數組/数组、加載、依賴。
- 一看到就刪：值得注意的是、事實上、總的來說、賦能、深入探討、打造、至關重要、進行 + 動詞。
Required Pre-Check
本檔的四張表常時生效，references 預設不讀。
- prose-style.md：寫連續散文才讀（專案文件、README 敘述段落、ADR、release note、規格書、簡報，或使用者說「太像 AI」「潤稿」）。要讀就在動筆前讀，不是寫完再回頭校對：稿子的段落結構一旦成形就很難拆，事後校對只改得動詞彙。實測讓模型自行安排順序，它會把這份排到最後一個動作，三篇稿子的骨架那時早就定了。commit message、程式碼註解、測試案例描述、表格與 API 參數說明不要讀：固定格式套散文節奏會壞掉，本檔的「AI 味速查」那層已經夠。
- 不要照抄本檔的外觀。本檔為了查閱方便用了大量粗體與表格，那是速查表的格式，不是你要產出的格式。散文就寫成散文：偽小標（獨立一行的
**……**）是明確禁止的，見下方「AI 味速查」第 4 條。 - guidelines.md：只在品質檢查未通過，或使用者要求稽核時讀。
- terms.csv：每次產出中文都要查，這是必要步驟，做法見下方「品質檢查與重寫流程」第 2 步。永遠
grep，不要整份讀：整份讀要數萬 token，grep 只回幾列。
Core Rules
- 使用繁體中文（zh-Hant-TW/zh-TW/zh_TW），並且使用在地慣用詞。
- 使用者說「用中文／中文回答／中文輸出」一律視為繁體中文，除非明確指定簡體（簡體／简体／zh-Hans／简中）。
- 術語用台灣慣例（資料、元件、應用程式、資料庫、伺服器）。
- 框架名稱、API、程式碼符號、檔案路徑保留英文。
- 檔案路徑不要做成連結，直接用反引號包住。
- 中文句子用全形標點，程式碼與路徑用半形標點。
關鍵術語速查表（必須遵守）
絕對禁用：代碼/代码、组件、異步/异步、回退、變量/变量、映射、對象/对象、數組/数组、函數/函数、返回值、導入/导入、導出/导出、依賴/依赖、數據/数据、應用程序/应用程序、數據庫/数据库、服務器/服务器、緩存/缓存、網絡/网络、加載、模塊、線程、默認/默认、用戶/用户
必用台灣術語：component 元件、array 陣列、object 物件、function 函式、data 資料、variable 變數、parameter 參數、return value 回傳值、import 匯入、export 匯出、async 非同步、cache 快取、load 載入、server 伺服器、database 資料庫、network 網路、thread 執行緒、module 模組、package 套件、dependency 相依性、default 預設、user 使用者
中國軟體圈行話禁用表（所有任務皆適用）
這些詞既是中國用語也是空話，換成具體動詞後句子會被迫說清楚到底做了什麼。寫專案文件、PR 描述、會議紀錄時最容易漏進來。
| 禁用 | 替代 |
|---|---|
| 落地 | 實作、實現、上線 |
| 復盤 | 檢討、回顧 |
| 沉澱（抽象物） | 累積、整理留存 |
| 閉環 | 完整流程；「形成閉環」→ 把流程走完 |
| 抓手 | 著力點、切入點 |
| 打通 | 整合、串接 |
| 顆粒度 | 細緻程度（技術文件的 granularity「粒度」可用） |
| 賽道 | 領域、市場 |
| 頭部（=領先者） | 龍頭、頂尖 |
| 痛點 | 台灣商業語境已通行；正式文件改「問題所在」「癥結」 |
一詞多義：看義項判斷，不是全面禁用
這幾個詞台灣也在用，只是義項不同，看義項判斷。下表是最常踩的幾個；其餘的查 terms.csv，clues／avoid_clues／note 三欄記的就是判斷條件。
| 詞 | 台灣保留的義項 | 這個義項要改 |
|---|---|---|
| 質量 | 物理學 mass | quality → 品質 |
| 水平 | horizontal | 標準、程度 → 水準 |
| 通過 | pass（通過考試、通過審查） | 藉由 → 透過 / 藉由 |
| 項目 | item（清單項目） | project → 專案 |
| 對齊 | 排版、資料結構對齊 | 會議上的「對齊」→ 同步、取得共識 |
| 數據 | 數值統計 | 泛稱 data → 資料 |
| 文件 | document | file → 檔案 |
| 並行 | concurrency | parallelism → 平行（中國的「並行」指 parallel，照抄會反過來） |
| 進程 | 進度、進展 | OS process → 行程 |
| 渲染 | 誇大；國畫暈染技法 | rendering → 算繪 |
| 遍歷 | 遍歷理論（Ergodic theory） | traverse → 走訪 |
What ships with it
11 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.
- LICENSE 2.9 KB
- README.md 6.4 KB
- references/guidelines.md 11 KB
- references/prose-style.md 11 KB
- references/README.md 3.6 KB
- references/terms.csv 157 KB
- scripts/audit_shared_glyphs.py 2.3 KB runs code
- scripts/fetch_terms.py 12 KB runs code
- scripts/lint_zhtw.py 17 KB runs code
- scripts/requirements.txt 190 B
- scripts/test_lint_zhtw.py 6.7 KB runs code
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.
- 11d ago First seen · 169 lines · 212 tokens per session scan A 096f01f81e45
zh-tw-writing is a skill published in the GitHub repository lanamaysu/agent-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 212 tokens to every session and 3,757 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…