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 jingjing-stylegit 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/jingjing-style)<a href="https://agentmods.dev/skills/tzengyuxio/skills/jingjing-style"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/jingjing-style/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/jingjing-style"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/jingjing-style.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 | $0.00211 | $0.05207 |
| Opus 5 | $0.00105 | $0.02603 |
| Sonnet 5 | $0.00042 | $0.01041 |
| Haiku 4.5 | $0.00021 | $0.00521 |
Grade A, and why
jingjing-style 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jingjing-style — 晶晶體改寫
把任何文章改寫成晶晶體——以中文為基底骨架，於句中嵌入「過於簡單、可被 中文替代且替代後無資訊損失」的英文單字或片語。讀完讓人覺得：說話者明 明可以一句中文講完，卻偏要 mix 一些 English。
晶晶體是 2016 年起的台灣媒體名媛口語現象——起源於該年 11 月某次時尚 雜誌專訪，名媛受訪時大量使用「我覺得很 amazing」「fashion 變成是像一個 life style」這類句法，被民眾戲稱為「晶晶體」並沿用至今。本 skill 模擬 的是這個語體現象本身，不針對任何個人。
一句話靈魂
不必要的英文字夾雜——替換進來的英文字必須是「過於簡單、可被中文取 代且替代後無資訊損失」的字（amazing / busy / happy / nice / big / hot / really / actually / so / kind of⋯⋯）。不可替換真正需要英文表達的詞 （專業術語、品牌名、人名、地名、無中譯詞）。炫耀感從「明明可以用中文 卻用英文」中產生——資訊損失等於零，語氣損失卻很大，這就是晶晶體的指紋。
Arguments
$0—（選填）Markdown 或純文字檔案路徑。若省略，請使用者提供內文， 或從對話上下文中找最近編輯的檔案。
Step 1: Load the Text
- 若提供
$0，讀取該檔案。 - 若無引數，找對話中最近撰寫或編輯的 Markdown 檔，或請使用者提供文字。
- 輸入可為任何語言。若非中文，先在心中譯為繁體中文（不必輸出），再做 晶晶體改寫。
Step 2: Decide Intensity
晶晶體有三段強度。若使用者未指定，預設 Medium。
| Level | 密度 | 效果 |
|---|---|---|
| Light | 每 4–5 句 1 處英文字夾雜 | 偶爾 mix 一個 amazing / nice / so，像剛從美國旅遊回來的朋友 |
| Medium（預設） | 每 2–3 句 1 處 | 明顯的中英夾雜習慣，PTT 上會被截圖那種 |
| Heavy | 每句 1–2 處 | 2016 年原汁原味，幾乎每句都有 1–2 個英文字 |
決定強度後在筆記裡標好：「強度 = X，預期密度 = Y」。
Step 3: Scan for Replaceable Words（白名單比對）
掃過整篇原文，圈出可替換為英文的詞彙——條件是「該英文詞夠簡單，國 中程度即懂；中文版本與英文版本資訊量等同；換了不會有人讀不懂」。
白名單核心集（可換）
形容詞 / 程度詞：
- amazing（驚奇／厲害／很棒）、nice（不錯／好）、cool（酷）、cute（可愛）
- big（大）、hot（熱／辣）、cold（冷）、happy（開心）、sad（難過）
- busy（忙）、tired（累）、easy（簡單）、hard（難）、boring（無聊）
- fancy（高級）、chic（時髦）、casual（隨性）、vintage（復古）、trendy（流行）
動詞 / 動作：
- check（確認）、try（試）、share（分享）、enjoy（享受）、handle（處理）
- care（在乎）、focus（專注）、support（支持）、book（預訂）、cancel（取消）
名詞 / 概念：
- fashion（時尚）、life style（生活方式）、style（風格）、vibe（氛圍）
- party（派對）、weekend（週末）、meeting（會議）、project（案子）
- background（背景）、idea（點子）、problem（問題）、feeling（感覺）
副詞 / 連詞 / 語氣詞：
- really（真的）、actually（其實）、so（所以／很）、kind of（有點）
- well（嗯）、I mean（我是說）、like（就像）、okay / ok（好）
- maybe（也許）、definitely（一定）、totally（完全）
黑名單（不可換）
- 真正需要英文的專業術語：algorithm、API、quantum、derivative、SaaS—— 這些保留英文是因為中譯損失資訊，不屬於晶晶體
- 品牌名 / 商標：Starbucks、Hermès、iPhone、Tesla——本來就是英文
- 人名 / 地名：Mary、John、Tokyo、New York——專名不算炫耀
- 無中譯或中譯極不通用的詞：bug（錯誤?）、debug、podcast、meme—— 中文圈本就常以英文使用
- 縮寫 / 首字母縮略：CEO、CPU、HTTP——這些屬於日常技術詞
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 · 289 lines · 211 tokens per session scan A c007f89345c3
jingjing-style is a skill published in the GitHub repository tzengyuxio/skills (46 stars, last pushed 2mo ago), licensed MIT. It adds 211 tokens to every session and 5,207 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…