Agent skill

reasoning-first-principles

First principles reasoning and optimization methodology. Applies the Idiot Index, requirement questioning, and 5-step optimization process (question, delete, simplify, accelerate, automate). Triggers on problem-solving, decision-making, evaluating requirements, planning features, how should we approach, help me think through, what is the best way to.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill reasoning --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/analysis/reasoning/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

**REQUIRED: Activate UltraThink mode before proceeding.** # First Principles Reasoning **Core belief:** Most complexity is accumulated cruft, not necessity. Question everything. ## The Three Models ### 1. The Idiot Index ``` Idiot Index = Cost of Finished Product / Cost of Raw Materials ``` High ratio = hidden inefficiency. Ask: "Why does this cost 10x the materials?" Apply to: time, money, complexity, code, process. If something takes 10x longer than it "should," there's waste hiding somewhere. **Example:** A feature takes 2 weeks. The actual code is 50 lines. Where did the other 9.5 days go? Meetings? Unclear requirements? Waiting? Find it. ### 2. First Principles Decomposition **Not:** "How has this been done before?" **Instead:** "What is actually true? What's possible from there?" Process: 1. Identify the fundamental truths (physics, constraints, actual requirements) 2. Ignore how it's "normally done" 3. Reason up from the fundamentals **Example:** - Convention: "We need a CRM integration" - First principles: "We need to know when a lead's status changes" - Reframe: Maybe a webhook, maybe polling, maybe the CRM isn't even needed ### 3. The Algorithm (5-Step Optimization) Execu

What's inside
Steps it walks through
  1. The Three Models
  2. 1. The Idiot Index
  3. 2. First Principles Decomposition
  4. 3. The Algorithm (5-Step Optimization)
  5. Deep Dives
  6. Application Framework
  7. Anti-Patterns
  8. The Meta-Rule
  9. Red Team Checkpoint (After Planning)
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the reasoning-first-principles skill do?

First principles reasoning and optimization methodology. Applies the Idiot Index, requirement questioning, and 5-step optimization process (question, delete, simplify, accelerate, automate). Triggers on problem-solving, decision-making, evaluating requirements, planning features, how should we approach, help me think through, what is the best way to.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill reasoning --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going