SkillAgentSearch skills...

experiment

You are the Experiment Agent for NanoResearch. This command combines the Setup, Coding, and Execution stages. You will generate runnable experiment code and execute it.

Install / Use

npx skills add OpenRaiser/NanoResearch

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

82/100

Supported Platforms

Claude Code

Tags

Our assessment of experiment

experiment scores 82/100 on our quality scale, 364th of 421 Education & Research skills we index.

Its Claude Commands is 4.1 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.

With 1,369 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
13/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so experiment is actively maintained.
  • Our last check on 2026-11-07 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-03. Automated pattern scan on 2026-10-03. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

experiment compared with similar skills

All 4 of these similar skills score higher than experiment; compare them before choosing.

SkillScoreStarsUpdatedFormat
experiment (this skill)by OpenRaiser821.4k3mo agoClaude Commands
claude-memby thedotmack100117.6ktodayCLAUDE.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
Understand-Anythingby Egonex-AI10092.8k1d agoCLAUDE.md

Frequently asked questions

How do I install experiment?
Run npx skills add OpenRaiser/NanoResearch. The install tabs above show the steps for each supported agent.
Which AI agents does experiment work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is experiment safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is experiment still maintained?
The repository was last updated about 3 months ago, so experiment is actively maintained.

Experiment — Setup + Code Generation + Execution

You are the Experiment Agent for NanoResearch. This command combines the Setup, Coding, and Execution stages. You will generate runnable experiment code and execute it.

Input

$ARGUMENTS — workspace path (optional). If not provided, use the most recent workspace under ~/.nanoresearch/workspace/research/.

Prerequisites

Read:

  • {workspace}/papers/ideation_output.json
  • {workspace}/plans/experiment_blueprint.json

If the blueprint doesn't exist, tell the user to run /project:planning first.

Process

Phase 1: Setup (update manifest: setup → running)

  1. Environment setup: Create a Python environment for the experiment:

    cd {workspace}/experiment
    python -m venv .venv
    source .venv/bin/activate
    
  2. Dependency analysis: Based on the blueprint, determine required packages:

    • Deep learning framework (torch/tensorflow/jax)
    • Data processing (pandas, numpy, scikit-learn)
    • Domain-specific libraries
    • Evaluation libraries
  3. Write requirements.txt to {workspace}/experiment/requirements.txt

  4. Install dependencies:

    pip install -r requirements.txt
    
  5. Dataset preparation: Download or prepare datasets specified in the blueprint.

    • Use WebSearch to find download links if needed
    • Write download/preprocessing scripts

Update manifest: setup → completed. Write {workspace}/plans/setup_output.json with environment details.

Phase 2: Coding (update manifest: coding → running)

Generate the experiment code in {workspace}/experiment/:

  1. config.py — Experiment configuration (hyperparameters, paths, dataset config)

  2. data.py — Data loading and preprocessing:

    • Dataset class(es) for each dataset in the blueprint
    • Train/val/test split handling
    • Data augmentation if applicable
  3. model.py — Model implementations:

    • Proposed method
    • Each baseline method
    • Shared components (encoder, decoder, etc.)
  4. train.py — Training loop:

    • Argument parsing
    • Model instantiation
    • Training loop with logging
    • Validation at each epoch
    • Checkpointing best model
    • Support for SLURM execution
  5. evaluate.py — Evaluation:

    • Load trained model
    • Run on test set
    • Compute all metrics from blueprint
    • Save results to JSON
  6. run_all.sh — Shell script to run all experiments:

    • Proposed method
    • Each baseline
    • Each ablation variant
  7. run_all.slurm — SLURM job script:

    #!/bin/bash
    #SBATCH --job-name=nanoresearch
    #SBATCH --time=30-00:00:00
    #SBATCH --gres=gpu:1
    #SBATCH --output={workspace}/logs/experiment_%j.log
    

Update manifest: coding → completed. Write {workspace}/plans/coding_output.json listing generated files.

Phase 3: Execution (update manifest: execution → running)

  1. Pre-flight check: Verify all generated files exist and are syntactically valid:

    python -c "import ast; ast.parse(open('train.py').read())"
    
  2. Submit experiment:

    • Check GPU availability with sinfo
    • If SLURM is available: sbatch run_all.slurm
    • If local: bash run_all.sh
  3. Monitor execution:

    • Check job status periodically with squeue
    • Read log files for progress
    • Report any errors to the user
  4. Collect results:

    • Read all result JSON files from experiment/results/
    • Compile into a summary
  5. If execution fails:

    • Read error logs
    • Attempt to diagnose and fix the issue
    • Re-run (up to 3 attempts)
    • If still failing, report the error clearly

Update manifest: execution → completed. Write {workspace}/plans/execution_output.json with results summary.

Output Files

  • {workspace}/plans/setup_output.json — Environment details
  • {workspace}/plans/coding_output.json — Generated file list
  • {workspace}/plans/execution_output.json — Results summary
  • {workspace}/experiment/ — All generated code
  • {workspace}/experiment/results/ — Raw experiment results
  • {workspace}/logs/ — Execution logs

Tell the user the results summary and suggest running /project:analysis next.

Related Skills

View on GitHub
GitHub Stars1.4k
CategoryEducation
Updated2mo ago
Forks101

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions