evaluate-attempt

Official

Validate benchmark attempts with precise metrics.

Authorbrazil-bench
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This SOP evaluates a completed brazil-bench attempt against the spec.md requirements, capturing metrics for comparison across orchestration patterns. It ensures consistent evaluation across Python and Swift/iOS projects.

Core Features & Use Cases

  • Conformance Metrics: automatically verify alignment with the benchmark spec and produce a structured report.
  • Multi-language Support: supports Python and Swift/iOS implementations, adapting checks to the language and tooling.
  • Use Case: after an attempt is completed, run this Skill to generate a leaderboard-ready report detailing conformance, test outcomes, and development timeline.

Quick Start

Run the evaluate-attempt skill against a repository and specify an output directory, for example: evaluate-attempt --attempt_repo=attempt-3 --output_dir=./results

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: evaluate-attempt
Download link: https://github.com/brazil-bench/pourpoise/archive/main.zip#evaluate-attempt

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.