Nanoresearch Experiment
Developmentnanoresearch-experimentNanoresearch Experiment is an Agent Skill for development published in the OpenRaiser/NanoResearch repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Generate a Python code skeleton from an experiment blueprint
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/OpenRaiser/NanoResearch/blob/HEAD/skills/nanoresearch-experiment/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/nanoresearch-experiment, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Experiment Skill
Purpose
Take the experiment blueprint and produce a runnable Python code skeleton that implements the proposed method, baselines, training loops, evaluation harness, and ablation configurations.
Tools Required
None. This skill operates entirely through LLM code generation based on the experiment blueprint.
Input
experiment_blueprint: Path topapers/experiment_blueprint.jsonproduced by the planning skill
Process
- Parse the experiment blueprint for datasets, baselines, metrics, and ablation groups
- Generate the project directory structure (data loaders, models, training, evaluation, configs)
- Produce data loading and preprocessing code for each specified dataset
- Implement model architecture stubs for the proposed method and each baseline
- Generate training loop with logging, checkpointing, and early stopping
- Implement the evaluation harness computing all specified metrics
- Create configuration files for each ablation group
- Add a main entry point that accepts a config and runs the full train-evaluate pipeline
Output
Produces experiments/ directory containing:
data/: Data loading and preprocessing modulesmodels/: Model architecture implementations (proposed method and baselines)training/: Training loop and optimization utilitiesevaluation/: Metric computation and result aggregationconfigs/: YAML configuration files for each experiment and ablation variantrun.py: Main entry point for launching experimentsrequirements.txt: Python dependencies