skills.rest
kaiohenricunha
kaiohenricunhaCOMMUNITY
Explore all skills by this author →
𝕏@kaiohenricunhaGitHub

create-experiment

Run scoped local experiments and generate dated markdown reports with comparison tables.

Updated Apr 14, 2026
Search Tags:#hypothesis testing#prototype#local development#reproducibility#experiment#decision validation#tooling comparison
One-click install
npx skills add https://github.com/kaiohenricunha/dotbabel --skill create-experiment
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-experiment
Source: https://github.com/kaiohenricunha/dotbabel/tree/main/plugins/dotbabel/templates/claude/skills/create-experiment
Command: npx skills add https://github.com/kaiohenricunha/dotbabel --skill create-experiment

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the messy, untracked ad-hoc tinkering that occurs when testing technical hypotheses or comparing competing approaches, ensuring every exploration produces a reproducible, documented result instead of lost terminal history.

Core Features & Use Cases

  • Structured Goal Refinement: Interactive workflow to align on clear success criteria and time boxes before starting any work, avoiding wasted effort on vague explorations.
  • Isolated Sandbox Execution: Runs all tests in separate git worktrees or local experiment directories to avoid polluting your main codebase.
  • Comprehensive Result Tracking: Captures all setup commands, execution outputs (including failures), generates comparison tables, and produces a dated markdown report with clear recommendations.
  • Use Case Example: Use this Skill to test if ripgrep is faster than grep on your repo, validate if switching from pnpm to bun improves install times, or prototype a new feature without modifying your main codebase.

Quick Start

Ask the AI to run a scoped experiment to test if ripgrep outperforms grep on your current repository, with a 30 minute time box and success criteria of at least 20% faster search times for large codebases.

Frequently Asked Questions about create-experiment

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

FAQPage Schema
How do I run a scoped local experiment to validate a technical hypothesis?▼

To run a scoped local experiment, use a structured workflow to define success criteria, execute tests in an isolated sandbox like a git worktree, and generate a dated markdown report with actionable recommendations.

What is the best way to compare competing development tools without polluting my main codebase?▼

Comparing competing development tools requires isolated sandbox execution in separate git worktrees or local experiment directories, capturing execution outputs to keep your main codebase clean and unmodified.

How do I track ad-hoc prototype validation results for reproducibility?▼

Track prototype validation results by capturing all setup commands and execution outputs, then generating a dated markdown report with comparison tables to ensure full reproducibility of your experiments.

Can I use this structured workflow for performance testing and feasibility checks?▼

Yes, you can use this structured workflow for performance testing and feasibility checks, applying it to proposed codebase or workflow changes by measuring results against predefined success criteria within a time box.

What are the limitations of running tooling comparisons in local experiment directories?▼

Running tooling comparisons in local experiment directories requires capturing all setup and execution commands manually, meaning any missed commands or undefined success criteria will reduce the reproducibility of the final report.

Related Skills

Explore More Software Engineering Skills→
passionseedpassionseed
2

using-git-worktrees

Create isolated git worktrees with safety checks and automatic project setup.

Official
Advanced
ShiienShiien
7

experiment-analyze

Parse experiment metrics and logs to assess significance against baselines.

Community
Intermediate
SimHackerSimHacker
49

evaluator

Evaluate outputs against rubric criteria and produce structured rationale.

Community
Basic
drxaibidrxaibi

continuous-agent-loop

Orchestrate continuous autonomous agent loops with quality gates and recovery controls.

Community
Advanced