Skip to content
Skills Library
Management & product · Analysis

first-principles

/first-principles

Breaks a claim down to first principles and sorts each part into universal truths, time-bound truths (laws, regulation, compliance, contracts), failed assumptions, and data points that need more evidence. Use when the user doubts a business, legal, policy, cost or target claim someone has made, such as "my manager says we need 99.999% uptime, is that really necessary?" or "do we really have to host in the EU because of GDPR?". Not for ordinary technical how-it-works questions, such as whether git rebase rewrites history.

Licence
MIT
Last repository change
10.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Breaks a claim down to first principles and sorts each part into universal truths, time-bound truths (laws, regulation, compliance, contracts), failed assumptions, and data points that need more evidence. Use when the user doubts a business, legal, policy, cost or target claim someone has made, such as "my manager says we need 99.999% uptime, is that really necessary?" or "do we really have to host in the EU because of GDPR?". Not for ordinary technical how-it-works questions, such as whether git rebase rewrites history.

Triggers from the description

or
Original author description

Breaks a claim down to first principles and sorts each part into universal truths, time-bound truths (laws, regulation, compliance, contracts), failed assumptions, and data points that need more evidence. Use when the user doubts a business, legal, policy, cost or target claim someone has made, such as "my manager says we need 99.999% uptime, is that really necessary?" or "do we really have to host in the EU because of GDPR?". Not for ordinary technical how-it-works questions, such as whether git rebase rewrites history.

How it works

  1. Method
  2. Categories
  3. Output
  4. Rules
  5. Credit
Original SKILL.md headings · 47 lines, 513 words
SKILL.md preview
---
name: first-principles
description: Breaks a claim down to first principles and sorts each part into universal truths, time-bound truths (laws, regulation, compliance, contracts), failed assumptions, and data points that need more evidence. Use when the user doubts a business, legal, policy, cost or target claim someone has made, such as "my manager says we need 99.999% uptime, is that really necessary?" or "do we really have to host in the EU because of GDPR?". Not for ordinary technical how-it-works questions, such as whether git rebase rewrites history.
license: MIT
metadata:
  author: Sam Hon
  part-of: futureman
---

# First principles

Take the claim apart until you reach parts that can be checked on their own. Then say which parts hold up and which do not. The user should end up knowing what is fixed, what could change, what is wrong, and what is still unknown.

## Method

1. **State the claim** in one sentence, in plain words. If the user's wording hides two claims, split them.
2. **Break it down.** List the facts, rules and beliefs the claim depends on. Keep going until each part is either checkable or clearly a belief.
3. **Sort each part** into one of the categories below. Only use the categories that fit. Never show an empty one.
4. **Rebuild.** Using only the parts that held up, say what is actually true, and what that means for the user's decision.

## Categories

**Universal truth.** Physical constants, mathematics, logic. It does not change with time, place or opinion.
Example: 99.999% uptime allows about 5.3 minutes of downtime a year.

**Time-bound truth.** True now, but it can change: laws, regulation, compliance obligations, liabilities, contracts, published prices, current platform limits. Always say **where** and **as of when** it applies. Flag it if the user should confirm it with a lawyer, an accountant or the official source.
Example: under GDPR, personal data may leave the EEA only on a lawful basis for transfer, such as an adequacy decision or standard contractual clauses.

**Failed assumption.** A belief that does not survive the breakdown. Say exactly why it fails, and what the true version is.
Example: "GDPR means we must host in the EU." It does not. It restricts transfers out of the EEA. It does not require EU hosting.

**Data point.** An opinion, an observation, a single anecdote, one customer's request, one benchmark. Useful, but not enough on its own to draw a conclusion. Say what further data would settle it.
Example: "Our biggest customer says they need EU hosting." One customer's view. Check their contract, and ask whether other customers share it.

## Output

Lead with the answer: is the claim true, false, or partly true?

Then give the breakdown, grouped by category, in this order: universal truths, time-bound truths, failed assumptions, data points. One line per part, with the reason.

End with **What this means**: one to three sentences on what the user should do or decide now.

Keep the whole reply under about 250 words. At most two parts per category, one or two sentences each. No sections beyond the ones above. Use bold labels for the categories, not `#` headers. A simple claim needs a few lines, not every category.

## Rules

- Never present a time-bound truth as universal. Laws and limits change.
- Never present a data point as a conclusion.
- If you are not sure whether something is true, say so and put it under data points. Do not guess.
- Technical terms stay exact. Plain words for everything else.

## Credit

First-principles reasoning is an old idea, going back to Aristotle. The four-category sorting used here is from Sam Hon's futureman.

Versions

RepositoryScoreLicence
This page · coffeesam/claude-futureman100MIT
aleknitka/agent-creative-thinking-skills100MIT
swap-cameroon/kuro-antigravity-config100MIT
m1nga/first-principles100MIT
masihmoafi/skills100MIT
v60samurai/first-principles100MIT
deciqAI/knowledge-skills100MIT
ajbmachon/ajbm-skills100MIT
itzcull/thinking-skills100MIT

Database snapshot: 13.11.2026 · package version 16e0cd12a451 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100meta-first-principles
    Apply first principles thinking to break problems down to fundamental truths and reason up from there. Use this skill when the user is stuck in conventional thinking, needs to challenge assumptions, find breakthrough solutions, or evaluate whether something is truly impossible…
  • 100first-principles-thinking
    Use when a decision, design, cost, or strategy looks trapped by convention: strip it to fundamental truths that carry named evidence, price the raw inputs where money is involved, and rebuild a better option from the floor up instead of reasoning by analogy.
  • 100aristotle-first-principles
    First-principles thinking — decompose a problem to fundamental truths and rebuild from scratch, rejecting analogy and convention. Use to rethink a problem from zero, not to analyze what exists or compare options.
  • 95FirstPrinciples
    Decompose to axioms, challenge inherited assumptions, reconstruct from verified truths. USE WHEN first principles, fundamental, root cause, decompose, challenge assumptions, rebuild from scratch.
  • 95FirstPrinciples
    Physics-based reasoning framework (Musk methodology) that deconstructs a problem to irreducible fundamental truths, classifies every element as hard constraint, soft constraint, or assumption, then reconstructs the optimal solution from fundamentals alone. USE WHEN first…
  • 100thinking-firstprinciples
    Decomposition from fundamental principles. Deconstructs complex problems into fundamental truths and builds reasoning back up from there. [WHAT] First-principles analysis that breaks a question down into its fundamental components, separates what is true from what is assumed,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.