skills.rest
lightrain-a
lightrain-aCOMMUNITY
Explore all skills by this author →
GitHub

idea-creator

Generate and rank research ideas from a user-provided direction.

Updated May 20, 2026
Search Tags:#literature review#ranking#research ideas#novelty check#pilot experiments#MCP codex#research wiki
One-click install
npx skills add https://github.com/lightrain-a/medtrace-aris --skill idea-creator-lightrain-a
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: idea-creator
Source: https://github.com/lightrain-a/medtrace-aris/tree/main/.vendor/aris/skills/idea-creator
Command: npx skills add https://github.com/lightrain-a/medtrace-aris --skill idea-creator-lightrain-a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the blank-page problem of turning a broad research direction into concrete, testable, publishable research ideas.

Core Features & Use Cases

  • Landscape survey: Scans existing local papers and recent literature to map sub-directions and identify gaps.
  • Idea generation & ranking: Brainstorms multiple candidate ideas, then filters and deep-validates the best ones using external LLM review.
  • Pilot experiments guidance: Proposes cheap pilot experiments to prioritize ideas with empirical signal before committing GPU time.

Quick Start

Ask for ideas by running: generate and rank research ideas for the direction you have in mind.

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 publishable research ideas, this Skill surveys existing literature to identify gaps, brainstorms hypotheses, and deep-validates candidates for feasibility and novelty to produce a ranked idea report.

What is a novelty check in research idea generation?▼

A novelty check filters brainstormed research hypotheses against recent literature and landscape context, ensuring candidate ideas are sufficiently distinct from existing work before ranking them.

How do I rank research ideas by feasibility before running experiments?▼

You rank research ideas by feasibility using external LLM review and proposed cheap pilot experiments, prioritizing hypotheses with empirical signal before committing GPU time.

Does this research idea generator work with a local research wiki?▼

Yes, the idea generator works with a research wiki by optionally updating it, while writing structured outputs to idea-stage/IDEA_REPORT.md and scanning local papers for landscape context.

Can I use Codex MCP for structured research idea review?▼

Yes, you can use Codex MCP for structured research idea review, applying it alongside WebSearch and WebFetch to generate landscape context and rank the filtered hypotheses.

Related Skills

Explore More Education & Research Skills→
LambenthanLambenthan
77

empirical-design

Generate an empirical research design from wiki pages with citations.

Community
Intermediate
TabithaFannyTabithaFanny

idea-creator

Generate, validate, and rank research ideas with pilot experiments.

Community
Advanced
ovachieverovachiever
52

literature-review

Plan and conduct multi-database literature reviews with screening and extraction.

Community
Advanced
WanLanglinWanLanglin

hypothesis-generation

Generate three to five testable hypotheses with predictions and experimental plans.

Community
Advanced