idea-discovery-robot

Frame robotics research problems and generate sim-first benchmark-grounded ideas with evaluation plans.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/jandan138/Auto-claude-code-research-in-sleep --skill idea-discovery-robot-jandan138
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: idea-discovery-robot
Source: https://github.com/jandan138/Auto-claude-code-research-in-sleep/tree/main/skills/idea-discovery-robot
Command: npx skills add https://github.com/jandan138/Auto-claude-code-research-in-sleep --skill idea-discovery-robot-jandan138

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill orchestrates a robotics-focused idea discovery workflow that converts broad research directions into testable, benchmark-grounded ideas, framed for sim-first evaluation and external review.

Core Features & Use Cases

  • Frames robotics problems from user input, conducts robotics-aware literature surveys, and generates concrete, benchmarkable ideas with structured evaluation plans.
  • Executes Phase 0 through Phase 5 workflows (framing, literature review, idea generation, novelty checks, and external review) to produce ready-to-run research concepts.

Quick Start

Initiate robotics idea discovery for 'robotics direction' and generate a framed problem plus top sim-first ideas.

Frequently Asked Questions about idea-discovery-robot

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

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

To generate testable robotics research ideas, frame the problem under embodied constraints and validate concepts using a sim-first, benchmark-grounded approach with explicit evaluation plans. This workflow converts broad directions into ready-to-run research concepts.

What is a sim-first validation approach for robotics idea generation?

A sim-first validation approach prioritizes testing robotics ideas in simulation environments before hardware deployment. It grounds idea generation in benchmarks, specifying required baselines, metrics, and potential risks to evaluate feasibility and novelty.

How do you conduct a robotics-aware literature survey for new research concepts?

Conducting a robotics-aware literature survey involves evaluating existing research to frame a specific problem and perform novelty checks. This process identifies required baselines and metrics, ensuring newly generated ideas are benchmark-grounded and distinct.

Can I automate benchmark evaluation planning for embodied robotics constraints?

Yes, you can automate benchmark evaluation planning for embodied robotics constraints by generating ideas with structured evaluation plans. This approach specifies required baselines, metrics, and potential hardware risks, proceeding only after explicit user approval.

What are the limitations of using benchmark-grounded idea generation for robotics?

The primary limitation of benchmark-grounded idea generation is the gap between simulation and real hardware. While sim-first validation mitigates risks by identifying potential hardware constraints early, real-world deployment requires additional testing beyond the initial evaluation plan.

Does idea generation for robotics include a novelty check against existing literature?

Yes, idea generation for robotics includes an explicit novelty check against existing literature. This step ensures the proposed sim-first, benchmark-grounded concepts offer a clear novelty path before proceeding to external review and hardware planning.