hai-idea

Evaluates ideas and returns a verdict with scorecard, objection, reframe, and validation test.

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/Rabbit-Ivan/Ivan-skills --skill hai-idea-rabbit-ivan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hai-idea
Source: https://github.com/Rabbit-Ivan/Ivan-skills/tree/main/skills/hai-idea
Command: npx skills add https://github.com/Rabbit-Ivan/Ivan-skills --skill hai-idea-rabbit-ivan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? It removes indecision when you are unsure whether an idea, feature, product, or project is worth pursuing, giving you one clear verdict instead of an endless list of pros and cons. ## Core Features & Use Cases - Five-Verdict Decision Framework: Every idea receives exactly one call — Do, Validate first, Reframe, Defer, or Kill — with a stated confidence level. - Dimension Scorecard: Scores pain, audience, workaround, leverage, timing, differentiation, feasibility, cost, risk, and proof path in a structured table. - Strongest Objection & Reframe: Names the single best reason not to proceed and proposes a stronger nearby version of weak ideas. - Use Case: You have three side-project ideas and limited weekends. Ask for an evaluation and get them ranked by decision value, each with a verdict and the cheapest test that could change the decision. ## Quick Start Use hai-idea to evaluate whether my idea for a subscription-based meal planning app is worth building or should be killed.

Frequently Asked Questions about hai-idea

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

FAQPage Schema
How do I evaluate whether an idea is worth pursuing?▼

Submit the idea for evaluation and receive one of five verdicts: Do, Validate first, Reframe, Defer, or Kill. The evaluation scores ten dimensions including pain, audience, timing, feasibility, and proof path, then states confidence and the cheapest test that could change the decision.

How to compare multiple ideas and decide which to build first?▼

Provide two or more ideas in one request and they are ranked by decision value rather than novelty. Each idea gets its own verdict, scorecard, and minimal validation test so you can prioritize based on evidence.

What verdicts can the idea evaluation return?▼

Exactly one of five calls: Do, Validate first, Reframe, Defer, or Kill. Each verdict includes a confidence level of high, medium, or low, plus the strongest objection even when the verdict is positive.

When should I not use idea evaluation?▼

Skip it when the decision to build is already made and you need execution plans, phases, or todos — use a goal-planning skill instead. It is also not suited for writing product requirements or purely choosing a name.

Does idea evaluation work for casual questions like should I build this?▼

Yes, it triggers on casual phrasing such as "is this worth my time" or "should I build this", not just explicit evaluation requests. It also supports Chinese triggers like 值不值得做 and 是不是伪需求.