Nanoresearch Planning

Takes a research hypothesis from ideation and turns it into a concrete experiment plan with datasets, baselines, metrics, and ablation groups. You'd use this after you've settled on which idea to pursue and need to map out the actual validation work. It parses your ideation output, identifies publicly available datasets that fit, pulls baseline methods from the literature survey, and designs ablations to isolate each novel component. The output is a structured JSON blueprint with resource estimates and timeline. Purely reasoning based, no external tools. Honest take: this is the unglamorous planning step that separates publishable research from interesting shower thoughts, and automating it means you spend less time wrestling with experimental design decisions.

GitHub stars: 1.5K
last updated: May 26, 2026

View on GitHub

Install

$ npx -y skills add openraiser/nanoresearch --skill nanoresearch-planning --agent claude-code

Installs into .claude/skills of the current project.

Files

Planning Skill

Purpose

Take the selected hypothesis from ideation and produce a detailed experiment blueprint specifying datasets, baselines, evaluation metrics, and ablation groups.

Tools Required

None. This skill operates entirely through LLM reasoning over the ideation output.

Input

ideation_output: Path to papers/ideation_output.json produced by the ideation skill

Process

Parse the selected hypothesis and supporting literature from the ideation output
Identify candidate datasets that are publicly available and appropriate for validating the hypothesis
Select 2-4 baseline methods from the surveyed literature for comparison
Define primary and secondary evaluation metrics aligned with the hypothesis
Design ablation groups that isolate each novel component of the proposed approach
Estimate computational requirements and timeline for each experiment
Compile everything into a structured experiment blueprint

SKILL.md on GitHub