idea-creator

Generate and rank publishable research ideas from a research direction.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/Shallow-W/llm-wiki --skill idea-creator-shallow-w
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: idea-creator
Source: https://github.com/Shallow-W/llm-wiki/tree/main/.claude/skills/idea-creator
Command: npx skills add https://github.com/Shallow-W/llm-wiki --skill idea-creator-shallow-w

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts a broad research direction into concrete, publishable research ideas and ranks them by feasibility, novelty risk, and expected impact.

Core Features & Use Cases

  • Landscape survey: Scans local papers and searches recent literature to map sub-directions and identify explicit structural gaps.
  • Idea generation + filtering: Brainstorms 8–12 ideas using an external LLM, then removes ideas that are infeasible, low-impact, or likely already done.
  • Pilot validation: Runs short, cheap GPU pilot experiments for the top candidates to re-rank based on empirical signal, then writes a structured IDEA_REPORT.
  • Optional wiki integration: If research-wiki/ exists, writes idea pages and (when available) adds edges and rebuilds the query pack for memory and traceability.

Quick Start

Ask the agent to run the idea discovery pipeline for your topic and return a ranked report: "Generate and rank research ideas for: [your research direction]".

Frequently Asked Questions about idea-creator

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

FAQPage Schema
How do I generate publishable research ideas from a broad direction?

To generate research ideas, provide a broad research direction and the pipeline surveys literature to identify gaps, brainstorms 8–12 ideas, filters by feasibility and novelty, and outputs a ranked report.

What is the best way to check research novelty and feasibility before planning experiments?

Checking research novelty and feasibility is handled by applying an external LLM review to filter brainstormed ideas, supplemented by running short GPU pilot experiments to obtain empirical signal for re-ranking top candidates.

How do I find structural gaps in recent literature for my research topic?

Finding structural gaps in recent literature involves scanning local papers and performing web searches to map sub-directions, which explicitly identifies areas where publishable research ideas can be generated.

Can I use GPU pilot experiments to validate research ideas before committing to a full study?

GPU pilot experiments can validate research ideas by running short, cheap tests on top candidates to gather empirical signal, allowing the system to re-rank ideas based on actual performance data.

Do I need a research-wiki directory to run the idea discovery pipeline?

A research-wiki directory is optional; if it exists, the pipeline writes idea pages and adds edges for memory and traceability, but the core ranking and report generation works without it.

What is included in the final ranked research idea report?

The ranked research idea report includes structured entries of top candidates ranked by expected impact, novelty risk, and feasibility, generated after literature review and pilot validation.