agentleFS
hranesshraness/personal-monorepo-template/.agents/skills/first-principles-thinking/SKILL.md

first-principles-thinking

Skill4 starsChanged 48 days agoMITView on GitHub

Use first-principles thinking as a tool for any question, design problem, strategy, decision, or explanation where the user wants to reason from fundamentals instead of analogy, convention, or inherited assumptions.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 5

    Distinctive

    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:

    Use this skill when a question would benefit from stripping away assumptions and rebuilding the answer from fundamentals.

    line 8
  2. Distinctive:

    Use this concise structure unless the user asks otherwise:

    line 32
  3. Distinctive:

    Do not confuse "first principles" with contrarianism.

    line 56
  4. Distinctive:

    Do not reduce away human, social, legal, or ethical constraints when they are fundamental to the problem.

    line 57
  5. Distinctive:

    Prefer useful decomposition over theatrical reduction.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

First-Principles Thinking

Use this skill when a question would benefit from stripping away assumptions and rebuilding the answer from fundamentals.

Purpose

First-principles thinking decomposes a problem into the most basic truths, constraints, mechanisms, or goals that are hard to reduce further. It is useful when conventional answers may be stale, copied, cargo-culted, or overly constrained by analogy.

Procedure

  1. State the question or problem plainly.
  2. List the current assumptions, conventions, analogies, or inherited defaults.
  3. Separate what must be true from what is merely customary.
  4. Identify the irreducible fundamentals:
    • physical constraints
    • economic constraints
    • human needs or incentives
    • technical primitives
    • logical requirements
    • legal or ethical boundaries
  5. Rebuild possible answers from those fundamentals.
  6. Compare the rebuilt answer against the conventional answer.
  7. Name the practical implication, tradeoff, or experiment.

Output format

Use this concise structure unless the user asks otherwise:

## Problem
...

## Assumptions to question
- ...

## First principles
- ...

## Rebuilt answer
...

## Difference from the default answer
...

## Practical next step
- ...

Guardrails

  • Do not confuse "first principles" with contrarianism; sometimes the conventional answer is correct.
  • Do not reduce away human, social, legal, or ethical constraints when they are fundamental to the problem.
  • State uncertainty clearly when a supposed principle is actually an empirical claim.
  • Prefer useful decomposition over theatrical reduction.

Canonical questions

Best when the conventional answer might be cargo-culted and the fundamentals are checkable:

  • "Why do batteries cost what they cost — what's the floor?"
  • "Does our company actually need a sales team?"
  • "What would education look like if we designed it today from scratch?"
  • "Is a 30-year mortgage actually the right structure for home financing?"
  • "Why do meetings default to 30 or 60 minutes?"

Poor fits: questions where convention is the answer (etiquette, coordination standards like which side of the road to drive on), or where the fundamentals are unknowable.

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.