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 making-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/making-decisions)<a href="https://agentmods.dev/skills/apple-ouyang/book-to-skill/making-decisions"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/making-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/making-decisions"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/making-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 | $0.00064 | $0.01974 |
| Opus 5 | $0.00032 | $0.00987 |
| Sonnet 5 | $0.00013 | $0.00395 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
making-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.
This is a copy
91% identical to Applicant Screening — 321 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
决策引导框架(WRAP)
第一步:快速分类
先判断决策性质,再决定投入多少精力:
| 维度 | 判断 | 策略 |
|---|---|---|
| 可逆性 | 可逆(换工具、试新方向) | 快决策,错了可以调整 |
| 可逆性 | 不可逆(结婚、辞职、大额投资) | 慢决策,走完整 WRAP |
| 投入度 | 低投入 | 直接试,不需要框架 |
| 投入度 | 高投入(核心资源、时间、金钱) | 走完整流程 |
亦仁原则:不可逆的决策要慢,可逆的决策要快。不要在状态很差时做决策(吵架后、深夜、极度疲惫时)。
WRAP 四步骨架
面临选择 → [思维狭隘] → W: 拓宽选择
分析选项 → [先入为主] → R: 验证假设 ← 调度子 Skill
做出选择 → [情绪影响] → A: 留出距离
接受结果 → [过度自信] → P: 准备出错 ← 调度子 Skill
W:拓宽选择
警惕信号:决策形式是「要不要做 X」「是否选 A」——这是思维狭隘的典型症状。只有 6% 的「是否」型决策被评为「非常好」,而有两个以上选项的决策有 40% 被评为「非常好」。
消失选项测试
如果当前所有选项都不可行,你会怎么办?
强迫自己离开现有选项,往往能发现真正的第三条路。
- Margaret Sanders 案例:纠结要不要开除接待员 Anna(业务能力强但不适合前台)。消除「开除 or 留下」的二选一后,发现第三条路——调岗做全职行政,前台用低成本实习生。
- $14.99 视频研究:问「买不买这部片?」75% 说买;改成「买这部片,还是留着 $14.99 买别的?」拒绝率从 25% 翻倍到 45%。仅仅提醒「还有其他选项」就改变了决策。
- 英特尔 CEO 格鲁夫:「如果我们被辞掉了,董事会推选上来一名新总裁,你认为他会怎么做?」
- 丈夫想辞职案例:妻子问「要不要让他辞职」,这是典型的「是否」型窄框架。消失选项测试:假设辞职被禁止,他被迫留在现有岗位 5 年,他会怎么做让现状变好?这个问题往往能发现「重新配置现有工作」的第三条路,比直接辞职更低风险。
机会成本思维
做这件事花的时间和钱,如果不做,还能做什么?
不只问「要不要做」,还要问「如果不做,剩下的资源能做什么更有价值的事」。
- 艾森豪威尔轰炸机案例:面对军费预算决策,艾森豪威尔把一架新轰炸机的成本换算成:多少所学校、多少座发电厂、多少家医院。这个「换算」让抽象的数字变成了真实的机会成本,迫使决策者正视「选这个就放弃了什么」。
赛马法(同时追踪多个选项)
不要只打磨一个方案,同时推进 2-3 个选项。同时评估多个方案的决策质量显著高于单一方案迭代。
- Anne Mulcahy 拯救 Xerox:接手濒临破产的 Xerox 后,Mulcahy 规定所有关键职位必须同时考察至少 3 名候选人,不允许只有一个选项。这个强制多轨制度让人事决策质量大幅提升,是 Xerox 复苏的关键因素之一。
「这个还是那个」→「既要也要」
当陷入二选一时,问:有没有办法同时得到两者的核心价值?
继任者问题
如果明天有人接替我的工作,他会怎么做?
用局外人视角打破路径依赖。
R:验证假设
警惕信号:你在「预测」某件事会不会成功,而不是去测试它。
→ 调度 /reality-testing-decisions(用实验替代预测)
警惕信号:决策感觉很明显,或者周围人都同意。
→ 调度 /seeking-disconfirming-evidence(主动寻找反对证据)
A:留出思考距离
警惕信号:情绪激动、被人催促、感觉「现在不决定就来不及了」。
10/10/10 法则
这个决定,10 分钟后我会怎么看?10 个月后?10 年后?
用时间拉伸判断决策的真实重量。很多「紧急」的决定,10 年后根本不重要。
- 丈夫辞职的 10/10/10:辞职后 10 分钟感觉很爽;但 10 个月后,如果还没找到新工作,感觉如何?这个时间拉伸让短期情绪冷却,暴露出「辞职前先找好下家」才是更理性的路径。
好朋友视角
如果是我最好的朋友面临这种情况,我会建议他怎么做?
把自己从当事人变成旁观者,情绪干扰立刻减少。Sophia 纠结了一整年要不要搬去芝加哥改善社交生活,问她「你会建议最好的朋友怎么做?」她脱口而出:「搬去芝加哥!」——答案一直在那里,只是被自己的恐惧挡住了。
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.
- 10d ago First seen · 150 lines · 64 tokens per session scan A e46dba8a5458
making-decisions is a skill published in the GitHub repository apple-ouyang/book-to-skill (130 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 1,974 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to Applicant Screening, differing in 321 lines, and is treated as a copy.
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…