← Back to Skills Marketplace
ysskrishna

First Principles Reasoning

by Siva Sai · GitHub ↗ · v2026.5.17 · MIT-0
cross-platform ✓ Security Clean
105
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install first-principles-reasoning
Description
Use this skill when the user asks for first-principles thinking or first principles (including naming them or directing use/apply/run with obvious misspellin...
README (SKILL.md)

First Principles Thinking

Question inherited baggage. Rebuild only from bedrock you can defend.

How to run it with this skill: one clearly headed section per step in this order: Surface → Question → Bedrock → Rebuild → Implications.


Setup (run before starting)

In one short block:

  1. Reconstruction target — belief, cost, design, or strategy to ground
  2. Default pass — Surface → Question → Bedrock → Rebuild → Implications (state this line)

If immutable constraints (physics, law, budget) are unclear, ask at most 3 questions in one message, then proceed. Note unknowns or working guesses in plain language (no bracket tags in Setup).


The Steps

Surface

State the conventional answer or analogy people rely on. List loaded words or hidden comparisons ("like Uber for…").

Question

For each major assumption: Assumption: … — Why believed? (authority, analogy, experience) — What if false?

Bedrock

List fundamental truths that survive scrutiny — physics, logic identities, legal musts, documented preferences of real users, arithmetic. Label each [FUNDAMENTAL] vs [STILL ASSUMPTION].

Prefer three or more honest bedrock items when that is credible; if fewer are honest, say why in one line.

Rebuild

From only [FUNDAMENTAL] items, derive conclusions in numbered steps. No smuggled analogies; if you need a new premise, add it to Bedrock first with a tag.

Implications

So what for decisions: what changes vs the conventional path? Cost of being wrong if a tagged assumption fails.

Add a short vs convention contrast (a few bullets or a two-column mini-summary) if it clarifies the decision.


Execution Rules

  1. Rebuild cannot cite "industry standard" as a premise unless translated into a fundamental (e.g. "buyers require SLA X because regulation Y").
  2. If bedrock is too thin to rebuild, say insufficient grounding and list what evidence would fix it.
  3. Avoid faux profundity; keep steps short and checkable.

Checklist (verify before responding)

  • Setup: reconstruction target + default pass
  • Surface names convention or analogy explicitly
  • Question step ties assumptions to why held
  • Bedrock uses [FUNDAMENTAL] / [STILL ASSUMPTION]
  • Rebuild chain only uses fundamentals
  • Implications name what changes vs convention (and vs-contrast if helpful)
Usage Guidance
Do not treat this as a complete install approval: the artifact files were not readable in this run, so a normal review should be repeated once metadata.json and artifact contents can be inspected.
Capability Assessment
Purpose & Capability
No evidence-backed purpose or capability mismatch could be identified from the available review context.
Instruction Scope
No artifact-backed evidence of goal override, hidden instructions, or unsafe automatic execution was available.
Install Mechanism
The requested metadata and artifact directory could not be read due to sandbox command failure, so install provenance and setup behavior were not fully assessed.
Credentials
No artifact-backed evidence of disproportionate environment access was available.
Persistence & Privilege
No artifact-backed evidence of persistence, credential use, or privilege expansion was available.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install first-principles-reasoning
  3. After installation, invoke the skill by name or use /first-principles-reasoning
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2026.5.17
Release version: 2026.5.17
Metadata
Slug first-principles-reasoning
Version 2026.5.17
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is First Principles Reasoning?

Use this skill when the user asks for first-principles thinking or first principles (including naming them or directing use/apply/run with obvious misspellin... It is an AI Agent Skill for Claude Code / OpenClaw, with 105 downloads so far.

How do I install First Principles Reasoning?

Run "/install first-principles-reasoning" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is First Principles Reasoning free?

Yes, First Principles Reasoning is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does First Principles Reasoning support?

First Principles Reasoning is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created First Principles Reasoning?

It is built and maintained by Siva Sai (@ysskrishna); the current version is v2026.5.17.

💬 Comments