agentleFS
ChianWChianW/C31/skills/core/C31-1st/SKILL.md

C31-1st

Skill1 starsChanged 3 months agoMITView on GitHub

追本溯源的思考框架。当用户提到"第一性原理"、"本质"、"追本溯源"、"底层逻辑"、"为什么"、或需要从基本原理重新构建解决方案时触发。用于将复杂问题拆解至最基础的公理级事实,从底层真理出发重新推导,而非依赖类比或经验模仿。

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When executing First Principles thinking, strictly follow these three steps:

    line 45
  2. Distinctive:

    If I remove the industry's default assumptions, what does the problem become?

    line 65
  3. Distinctive:

    Ignoring constraints: Only decomposing without reconstructing — failing to build a viable solution from the ground up

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Multilingual Triggers

LanguageTrigger phrases
ENC31-1st
ZH第一性原理, 追本溯源, 本质
JA第一原理, 本質を探る

Output language: Respond automatically in the user's conversation language.

First Principle Thinking

Trace back to the root, redefine — do not merely optimize.

Core Definition

First Principles Thinking is a method of breaking down complex things to the most fundamental physical or axiomatic facts, and then rebuilding solutions from those "ground truths" — rather than relying on analogy or imitating convention.

Analogical Thinking vs. First Principles

DimensionAnalogical Thinking (conventional)First Principles (ground-up innovation)
Starting pointFollow past experience, industry norms, or what others didStrip away surface appearances and target the irreducible essential elements
Reasoning methodInductive: others succeeded this way, so I'll do the sameDeductive: derive new solutions from fundamental laws and objective facts
End resultIncremental improvements and fine-tuning (optimizing what exists)Innovative breakthroughs and reconstruction (redefining what exists)

Classic Case: Elon Musk and SpaceX

Conventional thinking (analogical):

"Spacecraft have always been expensive — that's been true for decades. Buying a ready-made rocket is too costly, so lowering launch costs seems impossible."

First Principles:

"What are the core materials in a rocket? Aluminum, titanium, copper, carbon fiber. These raw materials are actually quite cheap on commodity markets — roughly 2% of the rocket's total price. So instead of buying finished products, we buy the raw materials and build it ourselves from scratch."

Result: Launch costs dropped to one-tenth or even one-hundredth of the original.

Practice Steps

When executing First Principles thinking, strictly follow these three steps:

Step 1: Identify and Define the Problem

  • Clearly state the specific problem to solve
  • Example: "Why is the product too expensive?" "Why does no one use this feature?"

Step 2: Decompose to Essential Facts

  • Keep asking "why"
  • Strip away all assumptions, conventions, and analogies
  • Retain only undeniable physical laws, mathematical axioms, or core elements
  • Key question: "If X were removed, would this thing still be itself?" If "no," X is essential. If "yes," X is an assumption.

Step 3: Rebuild from Fundamentals

  • Abandon "what does everyone else do"
  • Starting from the ground-level facts found in Step 2, derive a completely new solution upward
  • The answer may look entirely different from existing approaches

Self-Check Questions (answer before each use)

  1. Am I relying on analogy / experience / convention, or on ground-level facts?
  2. If I remove the industry's default assumptions, what does the problem become?
  3. From a physics / math / logic perspective, what is the minimum necessary composition of this thing?
  4. Is my solution derived from "what everyone else does" or from "what this thing must be"?

Common Pitfalls

  • Pseudo-first-principles: Decomposing only to "I think" or "experience tells me," not to "physics/mathematics proves"
  • Over-decomposition: Going all the way to quantum mechanics when it has no bearing on the actual problem. Decomposition depth should match problem complexity
  • Ignoring constraints: Only decomposing without reconstructing — failing to build a viable solution from the ground up

References

  • Elon Musk: "I think it's important to reason from first principles rather than by analogy."
  • Aristotle: "Each knowing about anything is based on first principles."
  • Duan Yongping: "Walk the right path."

"Boil things down to the most fundamental truths and reason up from there." — Elon Musk

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.