_run-and-analyze

Execute experiment scripts, analyze output files, and classify hypothesis outcomes.

2|1|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/inference-sim/sdlc-plugins --skill run-and-analyze
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: _run-and-analyze
Source: https://github.com/inference-sim/sdlc-plugins/tree/main/plugins/hypothesis-test/skills/_run-and-analyze
Command: npx skills add https://github.com/inference-sim/sdlc-plugins --skill run-and-analyze

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the execution of experiment scripts, analyzes their output, and interprets the results to determine the outcome of a hypothesis.

Core Features & Use Cases

  • Automated Experiment Execution: Runs run.sh scripts within specified hypothesis directories.
  • Output Verification: Checks for essential output files (config_a.txt, config_b.txt).
  • Analysis Script Execution: Runs analyze.py to process experiment outputs.
  • Result Interpretation: Classifies outcomes as Confirmed, Refuted, or Inconclusive based on metrics.
  • Use Case: After designing an experiment to test a caching latency hypothesis, this Skill will run the experiment, analyze the performance data, and provide a clear interpretation of whether the hypothesis was confirmed or refuted.

Quick Start

Use the _run-and-analyze skill to execute the experiment in the hypotheses/h3-caching-latency directory with the claim 'Caching reduces latency'.

Frequently Asked Questions about _run-and-analyze

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

FAQPage Schema
How do I automate experiment script execution and output analysis for hypothesis testing?

To automate experiment script execution and output analysis for hypothesis testing, you can use this Skill to run bash scripts, verify output files, and execute Python analysis scripts. It classifies results as Confirmed, Refuted, or Inconclusive based on parsed metrics.

What is the best way to interpret experiment results and validate hypothesis outcomes automatically?

Interpreting experiment results and validating hypothesis outcomes is handled by executing a Python analysis script on output files. The Skill compares metrics from config files to classify the hypothesis as Confirmed, Refuted, or Inconclusive.

Do I need bash and python3 to run automated experiment validation scripts?

Yes, you need bash and python3 to run automated experiment validation scripts, as the execution requires bash for `run.sh` and python3 for `analyze.py`. File I/O operations are also necessary for parsing and comparing output metrics.

How does automated analysis handle missing output files when testing a hypothesis?

Automated analysis handles missing output files by verifying the existence of essential files like `config_a.txt` and `config_b.txt` before running the analysis script. If these files are absent, the experiment results cannot be properly validated.

Can I use this for caching latency hypothesis testing and performance data analysis?

Yes, you can use this for caching latency hypothesis testing and performance data analysis. After designing your experiment, the Skill executes the scripts, analyzes the performance output, and provides a clear interpretation of whether the hypothesis was confirmed or refuted.