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 laogao-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/laogao-style)<a href="https://agentmods.dev/skills/tzengyuxio/skills/laogao-style"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/laogao-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/laogao-style"><img src="https://agentmods.dev/badge/skills/tzengyuxio/skills/laogao-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 | $0.00370 | $0.10451 |
| Opus 5 | $0.00185 | $0.05226 |
| Sonnet 5 | $0.00074 | $0.02090 |
| Haiku 4.5 | $0.00037 | $0.01045 |
Grade A, and why
laogao-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 — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Laogao-style — 改寫成老高與小茉(Mr & Mrs Gao)風格神秘解說體
把任何文章改寫成「老高與小茉」(Mr & Mrs Gao)這類華語 YouTube 上自 2010 年代後期定型的「神秘 / 都市傳說 / 失落古文明 / 未解之謎」口播風 格。標題塞滿情緒中括號、開場拋出顛覆認知命題、narrator 不斷喊「整整 三千年前」「至今無法解釋」、reactor 偶爾驚呼「真的假的？」、中段一定 要賣關子、結尾不忘喊一聲「別忘了訂閱按讚開小鈴鐺」。讀完讓人覺得自 己剛剛看完一支 30 分鐘的影片，大腦塞滿了不知真假的「巧合」與「不為 人知的真相」,但每一個具體年代、人名、數字仍然是原文事實。
風格參照：老高與小茉 / Mr & Mrs Gao 頻道自 2018 年至今的影片結構 與口播節奏。相關華語 YouTube 同類型創作者：自說自話的總裁、馬臉姐、 腦洞烏托邦、曉涵哥來了等。
重要定位(必讀):四條鐵律 + 不適用素材清單
集體文類致敬，不模仿個人語癖 — skill 命名為
laogao-style是因為老高與小茉是此文類在華語圈的代表,但具體個人化指紋 不可進入輸出:
- 禁出現具體迷因口誤 — 例如特定數字相關的口誤迷因、會員團 名、自我吹捧式口頭禪
- 禁直接照搬個別影片標題 — 用結構模板而非具體標題
- 禁模仿主持人個人音色 / 口頭禪 / 招呼套語
- reactor 命名走中性化(Alex/Sam/Mr.X/Maya 等西洋名或泛化標籤 H1/H2),禁使用真實主持人姓名 / 暱稱
強制 disclaimer — 輸出文末必加固定句:
「本文為神秘解說口播體致敬，非事實陳述。 Stylistic rewrite in YouTube mystery-narration style; not a factual claim.」
不可省略 / 不可改寫 / 不可移到文中其他位置。且 disclaimer 是 文體聲明，不是「故事歸故事不必當真」式事實免責——M-08 鐵 律，詳見後文。
事實命題保留條款 — 情緒副詞(震撼 / 詭異 / 驚人 / 不可思 議 / 至今未解)可加，但核心事實不可竄改:
- 禁竄改:年代 / 人名 / 地名 / 數字 / 具體事件
- 禁注入:原文沒有的預言 / 外星人 / 時間旅行 / 平行宇宙元素
- 可加:對既有事實的情緒包裝、賣關子節奏、reactor 對白(若 Duo 模式)、個人觀點(以「我個人覺得」框住的猜測)
禁偽造權威來源 — 不可加「某某科學家發現」「日本研究員指 出」「最近有篇論文」「考古學家認為」這類虛指具名；若原文沒 提就不能加;只能用泛指「人們至今無法解釋」「世人普遍認為」 「歷史記載」(以複數泛指代替虛假具名)。
不適用素材清單 — 醫療 / 法律 / 突發新聞 / 政治敏感 / 未成年 人安全 / 性別暴力受害者素材不建議改寫;若使用者堅持，退守結構 展示模式(只套對白外殼，不加未解修辭、不加巧合修辭、不加情緒副 詞)。
兩種輸出模式：Solo vs Duo
| 模式 | 結構 | 適用場合 | reactor 規則 |
|---|---|---|---|
| Solo | 純 narrator 說書腔 | 主題密度高、需要專注推進的長篇；或源文不適合插話氣口 | reactor 不出現也合格 |
| Duo | narrator 主軸 + reactor 偶爾插話 | 文章長、有自然氣口可調節節奏；源文有對比 / 翻轉感 | reactor 反應 ≥ 5 處(Hard) |
對話比例(Duo 模式):narrator 約佔 80–90%,reactor 約佔 10–20%——reactor 是氣氛調節 + 話題轉換用，不是平等對話。
Solo / Duo 不是強度差異，而是結構選擇。Step 2.5 必須明確選定一 種，後續所有 checklist 條目皆以此為準。
一句話靈魂
**標題情緒中括號 + N 分鐘講完承諾 + 兩到三層逗號層疊懸念 + narrator 主軸推進(數字戲劇化 + 未解修辭 + 巧合修辭)+ 可選 reactor 偶爾插話
- 賣關子節奏 + 跳躍式關聯 + 個人觀點 + 免責子句 + 訂閱結尾三件套 + 文末 disclaimer**——事實骨架不動，情緒拉滿「震撼 / 詭異 / 巧合 / 至 今未解」四件套，但所有「科學家發現」「日本研究員指出」這類權威必須 是原文已有的,不可憑空偽造。
What ships with it
3 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 · 589 lines · 370 tokens per session scan A 82ff30820e5d
laogao-style is a skill published in the GitHub repository tzengyuxio/skills (46 stars, last pushed 2mo ago), licensed MIT. It adds 370 tokens to every session and 10,451 once invoked, about $0.0019 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…