compare-runs

Compare two simulation runs to detect regressions or improvements.

Updated May 5, 2026
One-click install
npx skills add https://github.com/AratoAi/claude-code-plugin --skill compare-runs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compare-runs
Source: https://github.com/AratoAi/claude-code-plugin/tree/main/skills/compare-runs
Command: npx skills add https://github.com/AratoAi/claude-code-plugin --skill compare-runs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps users analyze differences between two simulation runs to detect regressions, improvements, or unchanged behavior, facilitating quality and performance assessments.

Core Features & Use Cases

  • Comparison of runs: Evaluate success rates, durations, and status discrepancies between two simulation runs.
  • Findings analysis: Identify new issues, resolved problems, and severity shifts in simulation outcomes.
  • Use Case: A QA engineer compares test runs before and after code changes to ensure new features haven't broken existing workflows and to verify improvements.

Quick Start

Use the compare-runs skill to compare two recent simulation run IDs from the same application to see if new issues appeared.

Frequently Asked Questions about compare-runs

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

FAQPage Schema
How do I compare two simulation runs to detect regressions?

To compare simulation runs and detect regressions, you need to list the run IDs, fetch their status and findings, and analyze the differences in success rates, durations, and severity shifts between the two test results.

What is simulation run comparison used for in QA and CI?

Simulation run comparison is used in quality assurance and continuous integration to detect regressions or improvements in test results, helping QA engineers verify that new code changes haven't broken existing workflows before deployment.

How do I identify new issues and resolved problems across test runs?

You can identify new issues and resolved problems across test runs by fetching the findings for both simulation runs and analyzing the differences to see which issues appeared, which were fixed, and if any severity shifted.

Can I use this to monitor performance changes between test results?

Yes, you can monitor performance changes between test results by comparing durations and success rates across simulation runs to detect whether recent modifications caused improvements or regressions in application performance.

What do I need to compare test runs before and after code changes?

To compare test runs before and after code changes, you need the simulation run IDs from the same application so the tool can fetch their respective statuses and findings to evaluate discrepancies.