af-skill-write-agent-benchmarks

Community

Benchmark AI agents with evidence-based tests.

Authorkorchasa
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmark AI agents under controlled, reproducible conditions to verify performance.

Core Features & Use Cases

  • End-to-end benchmarking with a standard evidence-based protocol.
  • Deterministic evaluation in isolated sandboxes with a judge and trace.
  • Applicable to coding, data analysis, and conversational agents in production-like scenarios.

Quick Start

Define a benchmarking goal, design an isolated sandbox, create a scenario, and run it through the Runner to obtain a structured verdict.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: af-skill-write-agent-benchmarks
Download link: https://github.com/korchasa/ide-rules/archive/main.zip#af-skill-write-agent-benchmarks

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.