search-benchmark

Community

Benchmark cross-model tool search quality.

Authordaltoniam
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmark Switchboard's search tool across models to measure cross-model search quality for tool discovery.

Core Features & Use Cases

  • Cross-model benchmark across opus, sonnet, and haiku in parallel
  • Generates a comparison table and identifies optimization opportunities
  • Use cases: performance assessment of search suggestions, model-tier differences, and when evaluating Phase 2 tag impact

Quick Start

Run the search-benchmark skill to dispatch identical scenarios to opus, sonnet, and haiku in parallel and generate a comparison report

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: search-benchmark
Download link: https://github.com/daltoniam/switchboard/archive/main.zip#search-benchmark

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 471,000+ vetted skills library on demand.