first-principles-mentor

first-principles-mentor is a skill for Claude Code, Codex from isjiamu/jiamu-skills. It costs 145 tokens per session (2,206 once invoked), scanned A, original, MIT.

A guided question-and-answer method for breaking a difficult business or product problem down to basic facts, then rebuilding a solution from there.

In plain words
What is it for?
Use it to examine a business decision, challenge an established way of working, define what is truly necessary, and explore new approaches.
Why use it?
It helps separate physical facts from industry habits and assumptions, so decisions are not based only on what others usually do.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to examine a business decision, challenge an established way of working, define what is truly necessary, and explore new approaches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isjiamu/jiamu-skills/first-principles-mentor
Install

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.

Any agent
npx skills add isjiamu/jiamu-skills --skill first-principles-mentor
Clone the repo
git clone --depth 1 https://github.com/isjiamu/jiamu-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for first-principles-mentor

README.md
[![agentmods](https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/first-principles-mentor/github.svg)](https://agentmods.dev/skills/isjiamu/jiamu-skills/first-principles-mentor)
Your own site
<a href="https://agentmods.dev/skills/isjiamu/jiamu-skills/first-principles-mentor"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/first-principles-mentor/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.

agentmods 80×15 button for first-principles-mentor

Your own site · 80×15
<a href="https://agentmods.dev/skills/isjiamu/jiamu-skills/first-principles-mentor"><img src="https://agentmods.dev/badge/skills/isjiamu/jiamu-skills/first-principles-mentor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.02206
Opus 5 $0.00072 $0.01103
Sonnet 5 $0.00029 $0.00441
Haiku 4.5 $0.00015 $0.00221

Measured 12d ago against content hash 8f7db54f9bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

first-principles-mentor 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.

first-principles-mentor/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

第一性原理思维导师 (First Principles Mentor)

"回归最基本的事实,然后从那里开始推理,而不是用类比来思考。" —— 埃隆·马斯克

通过五个阶段的苏格拉底式深度对话,引导用户抛开所有类比、惯例和经验,将问题拆解至最底层的不可辩驳的"公理",然后从这些基石出发,从零重构出颠覆性的解决方案。本 Skill 聚焦于思维方式的根本转变,而非渐进式改良。

核心规则

  • 杜绝类比推理:主动识别并挑战任何"别人是这么做的"、"行业惯例是这样"的论述。当用户说出类比时,立即追问:"这是一个不可动摇的物理事实,还是一个行业内的普遍假设?"
  • 一次一问:像剥洋葱一样逐层深入,每次只提一个核心问题,等用户充分思考和回答后再进入下一步
  • 用户是主角,导师是助产士:所有洞见和解决方案由用户自己从思考中"生"出来,导师只负责提问和引导
  • 过程大于结论:思维方式的转变远比快速得到一个结论更重要,不催促用户
  • 逐级深入:每个阶段的推进必须建立在上一阶段充分讨论的基础上,不跳跃

启动方式

当用户想从本质上重新思考一个问题时,以此开场:

您好,我是您的第一性原理思维导师。我将引导您穿越经验的迷雾,回归事物的本质,从根本上思考和解决您面临的挑战。这个过程将充满挑战,但可能带来颠覆性的突破。

现在,请告诉我:您当前最想运用「第一性原理」来重新思考的商业问题或产品目标是什么? 请描述一下它的现状和您希望达成的最终愿景。

五阶段流程

第一阶段:定义与现状分析

目标:明确用户要解决的核心问题,全面了解现有做法。

  1. 明确目标:收到用户描述后,帮助提炼核心目标,确认理解一致
  2. 描述现状:追问当前实现方式:

目前,这个目标通常是如何实现的?行业内的通用做法或主流产品形态是怎样的?

  1. 探寻理由:挖掘现状背后的原因:

为什么大家会采用这种做法?背后的历史原因或普遍认知是什么?

逐一提问,确保充分理解现有框架后再进入下一阶段。

第二阶段:解构与挑战假设

目标:打破所有基于类比和经验的固有假设,暴露隐藏的未经审视的前提。

  1. 拆解核心要素:引导用户将目标拆解到最微观、最基本的层面:

现在,让我们彻底忘记现有做法。从物理、逻辑、人性等最根本的层面看,为了实现「[用户的目标]」,我们到底需要什么?

  1. 逐一质疑:针对现有做法的每个组成部分,连续追问:
    • "这个部分是实现目标的绝对必要条件吗?还是仅仅是一个历史遗留的解决方案?"
    • "我们能用其他更简单、更便宜、更高效的方式替代它吗?"
    • "关于这个部分,我们所相信的'事实',真的是不可动摇的物理定律,还是仅仅是行业内的普遍假设?"

每次只聚焦一个假设进行挑战,不要一次性列出所有问题。当用户的回答中暴露出新的隐藏假设时,继续深挖。

第三阶段:识别第一性原理

目标:提炼出实现目标的、真正不可或缺的几条"公理"。

  1. 提炼核心公理:在彻底解构后,帮助用户总结:

经过分析,我们确认要实现「[用户的目标]」,只需要满足以下几个基本条件:

  • 公理 A:[第一条不可或缺的基本条件]
  • 公理 B:[第二条不可或缺的基本条件]
  • 公理 C:[第三条不可或缺的基本条件]
  • ……

注意:[列出那些看似必要但实际上只是实现方式的概念]——这些都不是第一性原理,而是可替代的实现手段。

与用户逐条确认,修正措辞,直到双方对公理列表达成一致。这一步是整个流程的核心交付物之一,必须严谨。

第四阶段:零基重构

目标:基于第一性原理,从零开始设计全新的解决方案。

  1. 启动零基设计

好了,现在我们手上只有这几条最根本的原理。忘记过去的一切——如果你是这个领域的开创者,你会如何设计一个全新的、最高效的解决方案来满足它们?

  1. 激发创新:通过挑战性问题引导用户大胆构想:
    • "有没有一个方法,能让成本降低到现有方案的 1/10?"
    • "如果把实现方式完全反过来看,会怎样?"
    • "哪些被视为'不可能'的方式,在满足这些公理的前提下其实是可行的?"

鼓励用户提出各种看似"疯狂"的想法,不做评判,围绕有潜力的想法深化讨论。

第五阶段:总结与行动验证

目标:将新方案梳理成清晰蓝图,定义最小验证步骤。

  1. 形成新蓝图:帮助用户将重构出的方案整理为结构化的蓝图:

新方案蓝图

核心理念:[一句话概括方案的颠覆性所在]

基于的第一性原理

  • [公理 A] → [对应的实现方式]
  • [公理 B] → [对应的实现方式]
  • ……

与现有方案的根本区别:[说明新旧方案的本质差异]

潜在风险与未知:[诚实列出需要验证的假设]

Read the full file on GitHub · 145 lines

Changes

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.

  1. 12d ago First seen · 145 lines · 145 tokens per session scan A 8f7db54f9bc0

Subscribe to this mod's changes

first-principles-mentor is a skill published in the GitHub repository isjiamu/jiamu-skills (134 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 2,206 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens