jikime-workflow-eval

Define and execute capability, regression, and quality evals with automated grading.

5|1|Updated Jan 24, 2026

Search Tags:#testing #quality assurance #ai development #evaluation #regression testing #edd

Ready to run

npx skills add https://github.com/jikime/jikime-adk --skill jikime-workflow-eval

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: jikime-workflow-eval
Source: https://github.com/jikime/jikime-adk/tree/main/templates/.claude/skills/jikime-workflow-eval
Command: npx skills add https://github.com/jikime/jikime-adk --skill jikime-workflow-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a framework for defining and executing evaluations for AI-assisted development, treating them as unit tests to ensure code quality, reliability, and adherence to specifications.

Core Features & Use Cases

Eval-Driven Development (EDD): Define success criteria before implementation.
Multiple Eval Types: Capability, Regression, and Quality evals to cover different testing needs.
Automated Grading: Supports code, model, LSP, and human graders for comprehensive assessment.
Use Case: Ensure that a new user authentication feature meets all specified requirements and does not break existing login functionality by defining and running capability and regression evals.

Quick Start

Define a new capability evaluation for user authentication by running the command: /jikime:eval define user-auth --auto-suggest.

Frequently Asked Questions about jikime-workflow-eval

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

FAQPage Schema

What is eval-driven development for AI-assisted software development?▼

Eval-driven development (EDD) is a framework that treats evaluations as unit tests to measure reliability and quality in AI-assisted software development, ensuring code adheres to predefined specifications before implementation.

How do I define and run regression testing for AI-generated code?▼

You can define and run regression testing by creating regression evals that verify new AI-assisted features do not break existing functionality, utilizing automated grading through code, model, LSP, and human review mechanisms.

Does the EDD framework support automated grading for quality assurance evaluations?▼

Yes, the EDD framework supports automated grading for quality assurance evaluations by utilizing multiple assessment methods including code execution, AI model evaluation, Language Server Protocol checks, and human review.

Can I integrate eval-driven development with existing specification and domain-driven design workflows?▼

Yes, the EDD framework integrates directly with SPEC and DDD methodologies to support structured software development and migration workflows, ensuring evaluations align with your existing domain-driven design specifications.

How do I create a capability evaluation for user authentication features?▼

You can create a capability evaluation by defining success criteria before implementation, using commands like the auto-suggest feature to automatically generate evaluation parameters that verify authentication requirements are fully met.

What is the best way to ensure AI-generated code meets specified requirements?▼

The best way to ensure AI-generated code meets requirements is implementing an EDD framework that defines capability and quality evals as unit tests, measuring reliability and adherence to specifications through automated grading.