compare-configs

Official

Compare agent config results

Authorsourcegraph
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps users understand the impact of different AI agent configurations by comparing their performance on benchmark tasks, highlighting where specific configurations succeed or fail.

Core Features & Use Cases

  • Benchmark Comparison: Analyzes results from multiple agent configurations (e.g., baseline vs. enhanced).
  • Divergence Analysis: Identifies tasks where configurations produce different outcomes (pass/fail).
  • Signal Identification: Pinpoints tasks where specific configurations show improvement or degradation.
  • Use Case: A researcher wants to know if a new "MCP" tool improves an AI agent's performance. This skill will compare the agent's results with and without the MCP tool enabled, showing which tasks benefit and which might be negatively impacted.

Quick Start

Compare the benchmark results across all agent configurations using the default JSON format.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: compare-configs
Download link: https://github.com/sourcegraph/CodeScaleBench/archive/main.zip#compare-configs

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.