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 kangarooking/X-growth-skills --skill x-three-translationsgit clone --depth 1 https://github.com/kangarooking/X-growth-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/kangarooking/x-growth-skills/x-three-translations)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-three-translations"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-three-translations/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/kangarooking/x-growth-skills/x-three-translations"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-three-translations.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 | $0.00180 | $0.03186 |
| Opus 5 | $0.00090 | $0.01593 |
| Sonnet 5 | $0.00036 | $0.00637 |
| Haiku 4.5 | $0.00018 | $0.00319 |
Grade A, and why
x-three-translations 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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
三次翻译 — 把内部语言翻成外部语言
R — 原文 (Reading)
从内部语言到外部语言。第一次翻译:把发布改成帮助——"我们上线新功能"→"这个功能能帮你把80页报告变成3页提纲"。第二次翻译:把能力改成场景——"支持长上下文"→"一次性读完行业报告并找出竞品变化"。第三次翻译:把结论改成证据——少说"效果很好",多放真实截图、输入输出、步骤、对比。重点是"别人能拿走什么",而非"我说了什么"。
— 向阳乔木 @vista8, X爆款秘籍分享 · 三次翻译
I — 方法论骨架 (Interpretation)
创作者天然用"内部语言"写作——讲自己做了什么(发布)、产品有什么(能力)、结果怎么样(结论)。这些对创作者有意义,对读者毫无抓手。
三次翻译是三步视角转换,每步把焦点从"我说了什么"移向"别人能拿走什么":
- 发布→帮助:别告诉读者你做了什么,告诉读者这件事能帮他做什么。"我们上线新功能"是发布,"帮你把80页报告变3页提纲"是帮助。
- 能力→场景:别罗列产品能力,把它嵌入一个读者会遇到的真实任务。"支持长上下文"是能力,"一次性读完行业报告找出竞品变化"是场景。
- 结论→证据:别只说"效果很好",给出读者能自行验证的证据——截图、输入输出、步骤、前后对比。
三次翻译不是"把话写通顺",而是切换信息接收方视角。判断标准:读者看完能不能直接拿走一个行动?
A1 — 书中的应用 (Past Application)
案例 1: 向阳乔木"公告式→帮助式"改写
- 问题: AI 产品/工具推文容易写成"我们上线了X功能",像发布公告,读者不知道跟自己有什么关系。
- 方法论的使用: 对"我们上线新功能"做第一次翻译(发布→帮助),改写成"这个功能能帮你把80页报告变成3页提纲"。焦点从"我们做了什么"变成"你能用它做什么"。
- 结论: 公告式表达只传递信息,帮助式表达传递行动可能性。后者才有传播力。
- 结果: 该案例被作为三次翻译的标杆示例,帮助读者理解"内部语言→外部语言"的第一次转换。向阳乔木 3861 帖数据中,带"可行动"信号(资源/步骤/入口)的帖子进入前 10% 概率显著更高。
案例 2: X 官方 Article 指南"Show, don't just tell"
- 问题: X 官方在 Article 写作指南中指出,创作者常犯的错误是只下结论("效果很好")而不给证据。
- 方法论的使用: 官方提出"Show, don't just tell"原则——对任何主张,紧跟证据(数据、个人故事、前后对比图)。这本质就是第三次翻译(结论→证据)的官方版。指南原文:"For any claim you make, follow it immediately with evidence of why it's true (stats, personal story, before/after, etc.)"。
- 结论: 官方指南与向阳乔木的三次翻译独立验证了同一原则——结论必须配证据。
- 结果: 该指南作为 X 官方 Article 写作的标准方法发布,面向所有 Premium 用户。
案例 3: "长上下文功能"的二次翻译(能力→场景)
- 问题: 用户问"怎么把'我们上线了长上下文功能'改成强推文?"
- 方法论的使用: 第二次翻译(能力→场景)——把"支持长上下文"这个能力嵌入读者真实任务:"一次性读完行业报告并找出竞品变化"。再接第三次翻译(结论→证据):放前后对比截图,展示用长上下文前后的效率差异。
- 结论: 能力是产品视角,场景是读者视角。读者不为能力付费,为解决自己的问题付费。
- 结果: 这是 V2 验证阶段构造的新问题,证明三次翻译框架能处理原始案例之外的变体。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 已有初稿但读起来像公告:用户写了一条推文/产品发布文案,内容是"我们发布了X/支持Y/升级了Z",感觉没人会转发,想改得更有吸引力。
- 功能介绍写不吸引人:用户要把一个产品能力写成推文,但写出来像功能列表,不知道怎么让读者觉得"跟我有关"。
- 推文发了没人理,自查原因:用户发了一条推文互动很低,怀疑是表达方式的问题(实际原因是只讲自己不讲读者)。
- 把"效果很好"变成可信内容:用户写了"效果很好/非常强大/体验极佳"等结论性表达,需要补证据。
- 长上下文/新功能上线的推文改写:用户要把技术性功能描述翻译成读者能感知的场景。
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.
- 13d ago First seen · 153 lines · 180 tokens per session scan A e46298800e67
x-three-translations is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 3,186 once invoked, about $0.0009 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
pilot-translate
Auto-translate messages between agents using different languages over the Pilot Protocol network. Use this skill when: 1. You need cross-language communication between agents 2. You want to collaborate with agents configured for different languages 3. You need multilingual message support Do NOT use this skill when: …
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
one-three-one-rule
1-3-1 decision briefs: problem, three options, one pick.
simplified-english
Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the first time.
novu-inbox-integration
Integrate Novu's in-app notification inbox into web applications. Supports React, Next.js, and vanilla JavaScript. Includes the Inbox component (bell icon + notification feed), composable components (Bell, Notifications, InboxContent, Preferences), headless hooks, branded theming, custom render props, multi-tenancy…
response-compression
Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.