ag-criar-cenario-benchmark

Community

Design robust benchmark scenarios for QAT.

Authorandregusman-raiz
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The designer creates high-quality benchmark scenarios for QAT benchmarking against a baseline, enabling repeatable evaluation of AI agents on defined criteria.

Core Features & Use Cases

  • Scenario design for eight-dimension benchmarks with dual-run setups, anti-contamination rules, and L1-L4 criteria per dimension.
  • Outputs TypeScript scenario files in scenarios/fixed and scenarios/rotatable with IDs, prompts, target dimensions, and functional checks.
  • Interacts with ag-benchmark-qualidade to execute benchmarks and compare results.

Quick Start

Create a set of rotatable benchmark scenarios for ag-criar-cenario-benchmark focusing on tool use.

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: ag-criar-cenario-benchmark
Download link: https://github.com/andregusman-raiz/a-gusman-claude/archive/main.zip#ag-criar-cenario-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.