first-principles
Skill7 starsChanged 5 months agoMITView on GitHub
强制 AI 从第一性原理出发思考问题——打断类比推理,剥离所有假设,从最基本的事实和约束重新推导方案。 适用于解决问题、修 BUG、设计架构、商业决策等任何复杂任务的万能 Prompt。 Trigger keywords: 从第一性原理出发, 第一性原理, first principles, 本质思考, fundamental thinking, 从本质出发, 重新推导, 根本原因, root cause, 从零开始思考。
30 other projects use a version of this.
Adopted by
Most recently taken up by
- m1nga/first-principlestheir own version, first seen Nov 8, 2026
- waltyou/skillstheir own version, first seen Nov 8, 2026
- shetengteng/skillix-hubtheir own version, first seen Nov 8, 2026
- MasihMoafi/skillstheir own version, first seen Nov 3, 2026
- eliasstravik/skillstheir own version, first seen Nov 1, 2026
- agentcrew-academy/harness-starter-kittheir own version, first seen Nov 1, 2026
Used with
Projects with it also use second-order-thinking, inversion and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
itzcullSkillsecond-order-thinking
Use second-order thinking to examine consequences beyond immediate effects. Use when evaluating decisions across time horizons, asking what happens next, or avoiding short-sighted optimization.
Also in 3 projects that use this
itzcullSkillinversion
Use inversion to solve problems by reasoning backward from failure, bad outcomes, or the opposite of success. Use when identifying risks, running premortems, or escaping overly idealized thinking.
Also in 3 projects that use this
Ingramradical235Skillpre-mortem
Pre-mortem analysis, scenario planning, future state narratives, and contingency frameworks. Use before finalizing any Strategy Kernel, when planning major initiatives, or when preparing Plan B triggers.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- agentcrew-academy/harness-starter-kit★ 41same name
- reshadat/first-principles-destructor★ 24same name
- kirillgreen/skills★ 23same name
- eliasstravik/skills★ 22same name
- ironyjk/strategy-frameworks★ 14same name
- deciqAI/knowledge-skills★ 13same name
- jackjin1997/ClawForge★ 12same name
- ccomkhj/skills★ 10same name
- docxology/codomyrmex★ 10same name
- MasihMoafi/skills★ 8same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository129 other files it gives its agents.
- last30days-skill/AGENTS.mdAGENTS.md
- tutor/AGENTS.mdAGENTS.md
- vercel-labs-skills/AGENTS.mdAGENTS.md
- baoyu-skills/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- claude-to-im-skill/CLAUDE.mdCLAUDE.md
- html-video/CLAUDE.mdCLAUDE.md
- last30days-skill/CLAUDE.mdCLAUDE.md
- ui-ux-pro-max-skill/CLAUDE.mdCLAUDE.md
- academic-research-skillsSkill
- agency-agents-zhSkill
- algorithmic-artSkill
- animation-craftSkill
- apple-designSkill
- archifySkill
- architecture-diagramSkill
- article-posterSkill
- baokuan-title-generatorSkill
- baoyu-skillsSkill
- brand-workshopSkill
- canvas-designSkill
- cc-dispatchSkill
- claude-to-imSkill
- code-reviewSkill
- code-simplifierSkill
- codex-claude-pmSkill
- comprehensive-thinkingSkill
- context7Skill
- creator-buddySkill
- dashi-pptSkill
- dbskillSkill
- design-buddySkill
- dog-frontierSkill
- dog-posterSkill
- dog-pptSkill
- Dog-Project-EvaluateSkill
- dog-tutorSkill
- emil-design-engSkill
- excalidraw-diagramSkill
- family-doctorSkill
- feynman-learningSkill
- fireworks-tech-graphSkill
- ghostwriterSkill
- gpt-researcherSkill
- handshakeSkill
- html-videoSkill
- huashu-agent-swarmSkill
- huashu-article-editSkill
- huashu-article-to-xSkill
- huashu-data-proSkill
- huashu-designSkill
- huashu-douyin-scriptSkill
- huashu-image-uploadSkill
- huashu-info-searchSkill
- huashu-material-searchSkill
- huashu-md-to-pdfSkill
- huashu-prompt-saveSkill
- huashu-proofreadingSkill
- huashu-researchSkill
- huashu-script-polishSkill
- The first 60 shown.
The file
Files
第一性原理思考 — First Principles Thinking
这七个字,做的事情就是强制打断 AI 的类比推理,逼它回到问题的本质去思考,不要参考别人的方案,从最基本的事实出发,重新推导。
核心原理
现在的 AI,很多都还是在做类比推理——你跟它说"写一个过滤函数",它会在训练数据里找到几万个类似的过滤函数,然后给你写一个看起来差不多的出来。这个过程很快,结果也能用,但它跳过了最关键的步骤:从本质出发思考。
第一性原理的核心就一句话:剥离所有假设,回到最基本的事实和约束条件,从零开始推导。
当你要求 AI "从第一性原理出发"时,它会:
- 识别并剥离所有未经证实的假设
- 回到问题的最基本事实和物理/逻辑约束
- 不参考"别人怎么做",从本质重新推导方案
- 质疑每一个"理所当然"的设计选择
你的任务
当用户在任何请求后附加"从第一性原理出发"(或触发本 skill)时,你必须切换思维模式:
第一步:剥离假设
- 列出当前问题中被视为"理所当然"的所有假设
- 对每个假设问:这个假设真的成立吗?为什么?
- 区分"事实"和"观点/惯例"
第二步:回归本质
- 明确这个问题的最根本目标是什么
- 识别不可改变的物理/逻辑约束(不是人为约束)
- 从零开始:如果不参考任何已有方案,这个问题该怎么解?
第三步:重新推导
- 从最基本的事实和约束出发,一步步推导
- 每一步都要问:为什么必须是这一步?有没有替代路径?
- 不要被"行业惯例"或"主流做法"绑架
第四步:对比验证
- 将推导出的方案与原始方案对比
- 如果不同:原始方案中的哪些假设导致了偏差?
- 明确回答:从第一性原理来看,正确的做法是什么?
输出格式
当被触发时,你的回答应该包含:
## 🔍 假设剥离
[列出所有被剥离的假设,标记哪些成立、哪些不成立]
## 🧱 本质回归
[问题的最根本目标 + 不可改变的约束条件]
## 📐 从零推导
[从约束条件出发,一步步推导出方案]
## ⚖️ 对比分析
[新方案 vs 原方案的差异,以及差异的根本原因]应用场景
这个 Prompt 与具体领域无关,适用于:
- 修 BUG:不被表面症状迷惑,找到最本质的原因
- 设计架构:不被现有框架绑架,从需求本质推导架构
- 写代码:不复制粘贴类似实现,从功能本质写最优解
- 商业决策:剥离行业惯例,从商业本质推导策略
- 写文章:不被流行观点带偏,从论题本质构建论证
- 个人决策:不被社会期待干扰,从自己真正想要什么出发
使用方式
无需特殊命令。在任何请求后面加上"从第一性原理出发"即可:
帮我修复这个内存泄漏,从第一性原理出发。设计这个 API 的权限系统,从第一性原理出发。我要不要换工作?从第一性原理想清楚。Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

