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 apple-ouyang/book-to-skill --skill reality-testing-decisionsgit clone --depth 1 https://github.com/apple-ouyang/book-to-skillWrote 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/apple-ouyang/book-to-skill/reality-testing-decisions)<a href="https://agentmods.dev/skills/apple-ouyang/book-to-skill/reality-testing-decisions"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/reality-testing-decisions/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/apple-ouyang/book-to-skill/reality-testing-decisions"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/reality-testing-decisions.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 | $0.00047 | $0.01590 |
| Opus 5 | $0.00023 | $0.00795 |
| Sonnet 5 | $0.00009 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
reality-testing-decisions 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 10d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用实验替代预测
任务目标
把"这个会不会成功?"的预测问题,转化为"怎么用最小成本验证?"的实验问题。
核心前提:我们对自己预测未来的能力严重高估。不要猜,不要感觉,去测试。
为什么预测不可靠
Tetlock 收集了 82361 个专家预测,结论:专家预测不如基本比率(用历史平均值外推),而基本比率又不如小规模实验。
额外的教育、20年经验、博士学位——都不能提高预测精度。反而,媒体曝光度越高的专家,预测越不准。
基本比率的力量:共同基金 vs 指数基金——基本比率数据如此清晰,以至于选共同基金几乎必然让你退休时更穷。当基本比率足够明确时,直接用它,不需要再做实验。
结论:只要有可能,就应该完全避免预测,用实验代替。
操作步骤
第一步:识别你在预测什么
把当前的问题写出来。如果它的形式是:
- "我觉得这个产品会有市场"
- "我感觉这个人能胜任"
- "我认为这个方向是对的"
这就是在预测。继续下一步。
第二步:设计最小实验
问:用什么最小行动,可以在现实中得到反馈?
不同场景的实验设计:
产品/项目验证
- CarsDirect 案例:不争论"网上卖车有没有人买",直接建个假网站,第一天卖出 3 辆车
- 亦仁原则:号是消耗品,先发垃圾内容让市场反馈,不要等到完美再发
- 默认项目都是通的,默认数据都是假的——对项目乐观去了解细节,对收入数据悲观谨慎投入
招聘/合作
- 面试表现和工作表现几乎不相关(医学院研究:面试排名第 700 和第 100 的学生,入学后表现无差异)
- 工作样本 > 面试:让候选人做一个真实任务,用结果评判,不用印象评判
- 希望实验室:给潜在员工 3 周咨询合约,"面试表现最佳的人常常工作表现最差"
- Steve Cole / HopeLab:$100k 设计项目,不赌一家公司,同时雇 5 家只做第一阶段($20k),用实际表现而非提案选人。从「OR 思维」转向「AND 思维」
职业/方向选择
- 想读药学院?先去药房工作几周,哪怕无薪
- NI 无线传感器:副总裁在投入 200-300 万前,先接了一个大学教授的小项目,走通了再加大投入
- 绝对不投入做任何无法亲自体验和感受的项目
大家都觉得不靠谱的想法
- 印度农民 app:库克和团队不看好,但让团队试了,农民收入提高 20%,最终 32.5 万农民使用
- 不试试怎么知道靠不靠谱?
创业验证
- 烘焙创业(Heath Brothers 案例):想开烘焙店,不要直接辞职全职投入。先在当地农贸市场摆一个月摊位,观察:有没有回头客?有没有盈利?盲测中你的产品排名如何?用真实市场反馈替代"邻居都夸我的布朗尼"式的自我确认。
- 药学院实习(Heath Brothers 案例):想读药学院的学生,先去 3 家不同药房各实习 1 个月,而不是直接报名。实习成本:时间。替代的错误成本:4 年学费 + 发现不喜欢这份工作。
第三步:渐进式实验(当恐惧阻止你测试时)
强迫症律师佩吉的 7 步实验——当你觉得"万一出错怎么办"时,把实验拆得更小:
- 把法律摘要带回家,做三次修改
- 做两次修改
- 做一次修改
- 晚下班一小时,把摘要留在办公室
- 按时回家,不做多余修改
- 刻意留下一个标点错误
- 刻意留下一个语法错误
结果:没有公司败诉,没有人被解雇,甚至没有人注意到错误。
原理:每完成一步,你就获得了真实数据,而不是继续在脑子里预测"天会不会塌"。
第四步:判断何时停止实验,直接跳入
实验不是拖延的借口。两种情况要区分:
- 杰森(应该实验):对海洋生物学感兴趣但不了解,先跟随一周,旁听几节课,确认后全力投入
- 马歇尔(不应该实验):已经确定需要学位,用"先上一节课试试"来拖延,这是逃避
- 丈夫想辞职(DecisiveWorkbook 案例):如果他在幻想另一份职业,先 ooch——赛车手梦想不像他想象的那么容易实现。但如果他已经确定要换工作,就设定触发条件("找到下一份工作再辞"),而不是无限期实验。
如果你已经确定了方向,小步尝试就是拖延。
注意事项
- 企业家和公司高管最大的区别:高管相信"预测未来才能控制未来",企业家相信"控制未来就不需要预测它"
- 60% 的世界 500 强 CEO 创业前没写过商业计划书——他们直接去卖
- 实验的成本要足够低:亦仁标准是验证一个项目总花费控制在一个月工资以内,优先找只需要时间不需要钱的实验
- 寻找反馈周期在三个月以内的实验;反馈周期太长,大多数人坚持不下去
What ships with it
1 file 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.
- 10d ago First seen · 117 lines · 47 tokens per session scan A 7089102d0fce
reality-testing-decisions is a skill published in the GitHub repository apple-ouyang/book-to-skill (130 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 1,590 once invoked, about $0.0002 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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…