eval-driven

Define, execute, and report software feature evaluations in development workflows.

Updated Jun 25, 2026
One-click install
npx skills add https://github.com/YuriNakayama/neurogolf --skill eval-driven
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: eval-driven
Source: https://github.com/YuriNakayama/neurogolf/tree/main/.claude/skills/eval-driven
Command: npx skills add https://github.com/YuriNakayama/neurogolf --skill eval-driven

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of eval-driven development by automating the definition, execution, and reporting of evaluations for features, making it easier to ensure quality and readiness.

Core Features & Use Cases

  • Define Evals: Create and manage evaluation definitions for features.
  • Check Evals: Execute evaluations to verify feature functionality and regression.
  • Report Evals: Generate comprehensive reports on eval status and results.
  • List Evals: Overview all defined evaluations.
  • Use Case: When you're developing a software feature, use the eval-driven skill to define the necessary checks, run them as you make changes, and get detailed reports on their status.

Quick Start

Define a new evaluation for a feature named 'feature-name' using the command '/eval-driven define feature-name'.

Frequently Asked Questions about eval-driven

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate evaluation checks for software features during development?

Automate software feature evaluations by defining markdown-based checks and executing them directly in your development environment to verify functionality and detect regressions. This streamlines TDD and BDD workflows with automated status reporting.

What is eval-driven development and how does it manage feature readiness?

Eval-driven development is a workflow that defines, executes, and reports evaluations for software features to ensure quality and readiness. It automates the creation of checks and generates comprehensive reports on feature functionality.

Can I generate reports for feature evaluations in a TDD or BDD workflow?

Yes, you can generate comprehensive reports on eval status and results directly within TDD and BDD workflows. The process logs markdown-based evaluation definitions and outputs detailed readiness reports after executing checks.

How do I define and list evaluations for software features?

Define evaluations for software features using markdown-based definitions and list all configured checks for an overview. This allows you to manage feature readiness and execute evaluations as you make code changes.

What's the best way to manage regression testing for feature development?

Manage regression testing by defining markdown-based evaluations for your features and executing checks as you make changes. This approach automates verification and generates detailed reports on feature functionality and status.