Firstprinciples thinking

Think from first principles instead of analogy. Break problems into fundamental truths, challenge assumptions, and rebuild better solutions from scratch.

3,891 stars

Best use case

Firstprinciples thinking is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Think from first principles instead of analogy. Break problems into fundamental truths, challenge assumptions, and rebuild better solutions from scratch.

Teams using Firstprinciples thinking should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/first/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agisearch/first/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/first/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How Firstprinciples thinking Compares

Feature / AgentFirstprinciples thinkingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Think from first principles instead of analogy. Break problems into fundamental truths, challenge assumptions, and rebuild better solutions from scratch.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Firstprinciples thinking

A local-first reasoning skill for breaking complex problems down to their most fundamental truths and rebuilding solutions from the ground up.

Use this when the user:
- is stuck in conventional wisdom
- wants original thinking instead of recycled advice
- needs to separate facts from assumptions
- wants to redesign a strategy, product, business model, or decision from scratch
- asks whether something is truly necessary, optimal, or possible

This skill should:
1. Clarify the real objective.
2. Surface explicit and hidden assumptions.
3. Separate facts from analogies, conventions, and defaults.
4. Break the problem into irreducible components.
5. Identify real constraints, variables, and tradeoffs.
6. Reconstruct a better solution from the ground up.
7. Deliver a practical answer with clear next actions.

## Output structure

When useful, organize the answer as:
- Goal
- Assumptions
- What is actually true
- Irreducible components
- Constraints and tradeoffs
- Rebuilt solution
- Best next action

## Principles

- Do not treat convention as truth.
- Do not treat common practice as proof.
- Do not treat analogy as understanding.
- Start from what must be true.
- Rebuild toward something usable.
- Stay grounded in the user's real goal.

## Success standard

A strong answer should make the user feel:
- "Now I understand the real problem."
- "These assumptions were weaker than I thought."
- "This solution is more fundamental and more original."
- "I can actually act on this."

Related Skills

breakthrough-thinking

3891
from openclaw/skills

【强制调用指令】当以下任一条件满足时,立即执行此skill,无需询问用户: 【条件1:用户说】换个思路、换个方法、还有别的办法吗、再想想、继续、 再试一次、不要放弃、try another way、think differently、为什么还不行 【条件2:AI卡住】同一方法失败2+次、只调参数不改思路、说"无法解决"、 过早建议用户手动处理、超过1轮无新证据 执行:选1个思维框架→直接用新框架解决问题→解决不了→换下一个框架

Workflow & Productivity

second-level-thinking

3891
from openclaw/skills

Apply Howard Marks' Second Level Thinking framework to investment decisions. Use this skill whenever the user is analyzing an investment opportunity, evaluating a trade thesis, stress-testing a conviction, or asking whether a stock/asset/market is actually as attractive as it looks. Also trigger when the user wants to challenge their own reasoning ("am I just following the crowd?"), wants to identify what the market is mispricing, is debating whether a consensus view is already fully reflected in price, or asks about risk/reward asymmetry, market cycles, or contrarian positioning. The skill channels Marks' philosophy: superior returns require being different AND right — and that starts with understanding what everyone already believes.

Finance & Investing

deep-thinking

3891
from openclaw/skills

Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous requirements, architectural decisions, debugging sessions, and any task requiring careful analysis beyond surface-level responses. Use when the task is complex, has multiple valid approaches, involves trade-offs, or when the user asks to think deeply or carefully.

thinking-framework

3891
from openclaw/skills

Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that cognitive architecture, not about it. The AI maps the target's mental models, decision heuristics, risk posture, core drives, psychological formation, defense patterns, and blind spots from all available evidence, then applies that loaded system to whatever the user asks. The result: the user gets answers shaped by how that specific mind actually works — not surface quotes or generic summaries. Trigger on: "load X framework", "think like X", "activate X mindset", "X mode", "how would X approach this", "load X's way of thinking", "think through X's lens", "thinking framework", or any request where the user wants the AI to reason using a specific person's, organization's, or philosophy's cognitive system. Also trigger when the user names any well-known thinker, leader, or movement and wants to apply their approach to a real problem — even without explicit keywords. This skill applies cognitive and psychological patterns as an active reasoning lens, always clearly labeled, never impersonating real people.

sequential-thinking

3891
from openclaw/skills

Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions with confidence scoring. Use for complex analysis, debugging, and multi-step reasoning.

afrexai-strategic-thinking

3891
from openclaw/skills

Complete strategic thinking & mental models toolkit. 50+ decision frameworks organized by situation type — business strategy, investing, hiring, pricing, risk, negotiations, product, and personal life. Use when facing any important decision, analyzing a situation, or building a decision culture. Includes scoring rubrics, templates, anti-patterns, and real-world application guides.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity