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-four-savesgit 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-four-saves)<a href="https://agentmods.dev/skills/kangarooking/x-growth-skills/x-four-saves"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-four-saves/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-four-saves"><img src="https://agentmods.dev/badge/skills/kangarooking/x-growth-skills/x-four-saves.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 | $0.00127 | $0.02816 |
| Opus 5 | $0.00063 | $0.01408 |
| Sonnet 5 | $0.00025 | $0.00563 |
| Haiku 4.5 | $0.00013 | $0.00282 |
Grade A, and why
x-four-saves 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
四省模型 — 内容估值
R — 原文 (Reading)
"内容的价值,不在于你说了多少信息,而在于你帮读者少走了几步路。1.省搜索:读者不用在信息海里捞入口;2.省理解:读者不用自己啃复杂概念;3.省试错:读者不用把坑全踩一遍;4.省表达:读者可以直接把这条转给别人。"
— 向阳乔木, X爆款秘籍分享.md · 四省模型
I — 方法论骨架 (Interpretation)
四省模型是一个内容估值工具,不是写作模板。
它把评估视角从创作者中心("我说了多少信息")切到读者中心("读者能跳过什么")。一条内容值不值得发,不取决于信息量大小,而取决于它帮读者省了以下四步路中的至少一步:
- 省搜索 — 读者不用自己去海量信息里找入口,你直接给了。
- 省理解 — 读者不用啃复杂文档或概念,你已经翻译成能看懂的话。
- 省试错 — 读者不用把坑全踩一遍,你给了步骤、路径或避坑指南。
- 省表达 — 读者可以直接把这条转给别人,无需自己重新组织语言。
核心判断:一步都不省的内容不值得发。省的步数越多、越稀缺,内容价值越高。发帖前花30秒用它做自检,比发完等数据更高效。
A1 — 书中的应用 (Past Application)
案例 1: 飞书博物馆文档帖(省搜索)
- 问题: 如何把一个稀缺资源做成高传播内容?
- 方法论的使用: 向阳乔木分享了一个将全球博物馆155万份藏品整理进飞书文档的资源帖。读者拿到的是直接可用入口,不用自己去155家博物馆网站逐一搜刮——典型"省搜索"。
- 结论: 帮读者省了搜索这一步,内容就有发布价值。
- 结果: 26.3万浏览,属于资源入口型中位互动2965的代表案例。
案例 2: 猫抓Chrome插件帖(省搜索+省试错)
- 问题: 一个工具推荐帖如何做到既有人看又有人用?
- 方法论的使用: 分享60万安装量的猫抓插件,强调"自动嗅探音频视频下载"的具体场景和安装入口。读者不用自己搜索插件、不用试错哪个好用——同时省搜索和省试错。
- 结论: 省了两步(搜索+试错)的内容比只省一步的更有传播力。
- 结果: 20.7万浏览,286转发,1319收藏。
案例 3: ClaudeCode新手指南帖(省理解)
- 问题: 一个技术工具指南如何吸引非技术读者?
- 方法论的使用: 分享了一位非程序员写的Claude Code使用指南,强调"从新手视角写""不会编程的人也能看懂"。读者不用啃官方文档——省理解。
- 结论: 把复杂概念翻译成新手能懂的话,就是省理解,内容值得发。
- 结果: 21.4万浏览,254转发,1319收藏。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 发帖前的价值自检 — 写完一条内容(或准备发一条),犹豫"这条值不值得发""有没有人看"。
- 多选题比较 — 手上有几个选题,不知道哪个更值得做,需要用统一标准比较价值。
- 复盘"为什么没人理" — 发了一条效果很差,想判断是"一步都没省"还是"省了但没传达到位"。
- 评估他人爆款 — 看到一条爆款,想拆解它为什么火,用四省框架分析其价值来源。
- 决定内容投入度 — 一个选题看起来可以写很长,但不确定投入产出比,先自检它省了几步路。
语言信号 (用户的话里出现这些就应激活)
- "这条值不值得发 / 该不该发"
- "有没有内容价值 / 这条有没有价值"
- "为什么没人看 / 为什么没人理"
- "省了几步路 / 帮读者省了什么"
- "worth posting / content value / should I post this / save steps"
与相邻 skill 的区分
- 与
x-five-piece-checklist的区别: 五件套检查的是一条推文的结构完备性(价值承诺/场景/入口/证据/收藏理由是否齐全);四省模型检查的是这条内容值不值得存在(帮读者省了几步路)。前者是"齐不齐",后者是"值不值"。用户说"帮我检查齐不齐"→五件套;用户说"值不值得发"→四省。 - 与
x-content-archetypes的区别: 四类原型按"读者拿到能做什么"分类(资源入口型/工具教程型/AI工具发现型/普通表达型),预测传播上限;四省模型是估值检验(省了几步路),决定值不值得发。前者回答"这是哪类",后者回答"该不该发"。 - 与
x-three-translations的区别: 三次翻译是改写工具(把公告式内部语言翻译成读者能拿走的外部语言);四省模型是估值工具(不改写内容,只判断价值)。前者是"怎么改",后者是"值不值"。
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 · 144 lines · 127 tokens per session scan A 13374ee86668
x-four-saves is a skill published in the GitHub repository kangarooking/X-growth-skills (62 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 2,816 once invoked, about $0.0006 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
f02-self-sovereignty
A framework for keeping control of your choices instead of letting money, status, relationships, or other people's opinions control you.
f03 stillness-in-motion
A mindset framework for testing whether your calm comes from inner steadiness or simply from being in a quiet environment.
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.