idea

Generate literature-grounded research directions and hypotheses for AI research agents.

1|Updated May 15, 2026
One-click install
npx skills add https://github.com/BoomberAsp/DeeperScientist --skill idea-boomberasp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: idea
Source: https://github.com/BoomberAsp/DeeperScientist/tree/main/src/skills/idea
Command: npx skills add https://github.com/BoomberAsp/DeeperScientist --skill idea-boomberasp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps in shaping research directions and hypotheses, providing concrete, literature-grounded, and frontier-aware directions for AI-powered research agents.

Core Features & Use Cases

  • Research Direction Selection: Offers guidance on selecting the next executable research route based on current objectives and bottlenecks.
  • Literature Search Integration: Integrates with literature search to inform the ideation process.
  • Candidate Idea Generation: Generates a small, meaningfully different slate of candidate ideas for further exploration.

Quick Start

Use the idea skill to generate a research direction for the current objective and bottleneck.

Generate a research direction for the objective "Improve model accuracy on the ImageNet dataset" and the bottleneck "Overfitting during training".

Frequently Asked Questions about idea

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

FAQPage Schema
How do I generate research directions based on literature search?

To generate research directions from a literature search, analyze prior work to identify key contradictions and bottlenecks. This process focuses on finding novel mechanisms to propose concrete, frontier-aware hypotheses for AI-powered research agents.

What is hypothesis generation for AI research agents?

Hypothesis generation for AI research agents is the process of shaping executable research routes by analyzing current objectives and bottlenecks. It produces a small slate of meaningfully different candidate ideas for further exploration.

How do I select a research direction when facing a specific bottleneck?

Select a research direction by defining your current objective and the specific bottleneck you face, such as overfitting during training. The system then offers guidance on the next executable research route to overcome that challenge.

Can I use this to find novel mechanisms for my research objective?

Yes, you can use this to find novel mechanisms by requiring comprehensive literature search and analysis of prior work. It identifies opportunities within the current research landscape to shape frontier-aware directions for your objective.

What is the best way to identify important contradictions in prior work?

The best way to identify important contradictions in prior work is through a comprehensive literature search integrated with the ideation process. This approach focuses on finding bottlenecks and opportunities within the current research landscape.