dare

Decomposes problems into first-principles assumptions and rebuilds solutions through chained subagent reviews.

Updated Aug 30, 2026
One-click install
npx skills add https://github.com/ryanportfolio/threejs-interview-test --skill dare-ryanportfolio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dare
Source: https://github.com/ryanportfolio/threejs-interview-test/tree/main/.agents/skills/dare
Command: npx skills add https://github.com/ryanportfolio/threejs-interview-test --skill dare-ryanportfolio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Teams often solve the wrong problem because unexamined assumptions go unchallenged. This Skill applies a first-principles reasoning chain that decomposes a problem, audits every assumption, recombines only the surviving building blocks, and tests the result against reality. ## Core Features & Use Cases - Structured Decomposition: Breaks a problem statement down into its fundamental assumptions and components. - Independent Audit Chain: Each step runs as a fresh subagent fed only the prior artifact, preventing context contamination and self-review bias. - Assumption Filtering: Recombines only the blocks that survive scrutiny, then validates the rebuilt solution against real-world constraints. - Use Case: When a team asks "are we solving the right problem" about a product roadmap or architecture decision, invoke this Skill to strip the problem to first principles and rebuild a defensible answer. ## Quick Start Ask the assistant to run the dare skill on your problem statement, for example by saying "use first principles to check whether we are solving the right problem with this feature".

Frequently Asked Questions about dare

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I apply first-principles thinking to a product problem?▼

Invoke the dare skill with your problem statement. It decomposes the problem into assumptions, audits each one in an independent subagent step, recombines the surviving blocks, and tests the rebuilt solution against reality.

What is the dare skill used for?▼

The dare skill runs a first-principles reasoning chain to check whether you are solving the right problem. It triggers on $dare, 'first principles', or 'are we solving the right problem' and produces an assumption-audited solution.

Why does each step run as a separate subagent?▼

Each step is a fresh subagent fed only the prior artifact so earlier reasoning cannot bias later stages. This prevents self-review and keeps the assumption audit independent at every stage of the chain.

Can I use this skill in a Codex environment?▼

Yes, the SKILL.md acts as a Codex adapter that reads the canonical workflow from .claude/skills/dare/SKILL.md. It requires the session to expose multi-agent tools and applies the compatibility notes in .agents/CODEX-SKILL-COMPATIBILITY.md.

When should I not use a first-principles chain?▼

Avoid it for routine, well-understood tasks where assumptions are already validated, since the multi-stage subagent chain adds latency. It is best reserved for ambiguous or high-stakes problem framing.