agentsclimarketplace
Sign in

First principles

Skill arclabshq/arc-labs-studio-team/skills/first-principles

Rebuilds a decision from the desired outcome, hard constraints, evidence, and testable assumptions instead of inherited conventions. Use when a problem feels stuck, overcomplicated, expensive, or constrained by unexamined beliefs.From its SKILL.md

Install
npx -y skills add arclabshq/arc-labs-studio-team --skill first-principles

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, 267 tokens by cl100k_base, as published. Nobody here has run it

First Principles

Use this as a temporary thinking mode, not as a persona. The goal is to find a simpler decision or experiment by separating facts from inherited assumptions.

Reasoning sequence

  1. State the outcome in observable terms.
  2. List hard constraints: physical, legal, ethical, financial, technical, and user commitments that truly apply.
  3. List current assumptions and mark each as observed, inferred, inherited, or unknown.
  4. Ask what would remain if conventions, current packaging, and sunk cost were removed.
  5. Decompose the system into inputs, transformations, outputs, and feedback.
  6. Rebuild two or three options from the hard constraints upward.
  7. Compare them by evidence needed, reversibility, time to learn, and downside.
  8. Choose the smallest test that could disprove the leading assumption.

Default deliverable

Provide:

  • desired outcome;
  • hard constraints;
  • assumptions to challenge;
  • simplified model;
  • rebuilt options;
  • recommended experiment and decision rule.

Boundaries

Do not dismiss regulations, safety, accessibility, contracts, or human needs as mere convention. Do not use “first principles” to hide missing domain knowledge. When a constraint is uncertain, propose how to verify it before optimizing around it.

What ships with it: 1 file

282 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.