From clab
Provides standard experiment folder structure with templates for config.yaml, report.md, reproduce.py, and pre-flight checklist. Use to create or validate research experiment directories.
How this skill is triggered — by the user, by Claude, or both
Slash command
/clab:experiment-structureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Standard structure for experiments in this research project.
Standard structure for experiments in this research project.
mkdir -p experiments/exp_NNN_name/{outputs,judgments,scratch,suggested_utils}
name: exp_NNN_name
description: |
[What this experiment tests]
# Parameters
# [Add experiment-specific parameters]
# Expected outputs
# [What files/data this should produce]
# Experiment Report: exp_NNN_name
## Experiment
[What you tested]
## Method
[How you ran it - commands, configs, tools used]
## Observations
[Raw results, verbatim outputs]
## Judgments
[Aggregated scores, patterns - if applicable]
## Anomalies
[Anything unexpected]
## Data
- **Outputs**: `outputs/`
- **Judgments**: `judgments/`
- **Reproduction**: `reproduce.py`
#!/usr/bin/env python3
"""Reproduce key results from this experiment."""
def main():
# TODO: Add reproduction steps
pass
if __name__ == "__main__":
main()
Before running an experiment, verify the folder has:
config.yaml with experiment parametersreport.md (can be empty template)outputs/ directoryjudgments/ directory (if using judges)scratch/ directory (for throwaway code)suggested_utils/ directory (for proposing reusable code)If anything is missing, create it using the templates above.
npx claudepluginhub butanium/claude-lab --plugin clabProvides instructions for creating and using experiment.md files to test ideas, configurations, or code snippets in Claude Code.
Plans experiment protocols, result tables, mock data, evaluation gates, method traceability, and table schemas for research papers before real results exist.
Organizes research project directories with a standard scientific skeleton. Use when scaffolding new projects, restructuring existing codebases, or enforcing DVC-tracked data pipelines for reproducible experiments.