source-command-evaluate

Evaluate code implementations against a predefined contract via adversarial review.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/jmolz/m0lz.02 --skill source-command-evaluate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: source-command-evaluate
Source: https://github.com/jmolz/m0lz.02/tree/main/.agents/skills/source-command-evaluate
Command: npx skills add https://github.com/jmolz/m0lz.02 --skill source-command-evaluate

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of evaluating code implementations against a predefined contract, eliminating manual reviews and bias, and ensuring quality standards are met.

Core Features & Use Cases

  • Contract-Based Evaluation: Grading code against a contract to ensure adherence to specifications.
  • Adversarial Review: Conducting a parallel adversarial review to challenge design assumptions and identify potential failures.
  • Use Case: Use this Skill to automatically evaluate a code change against a contract, identify issues, and provide feedback before merging into the main codebase.

Quick Start

Run the /evaluate command with the path to the plan file, e.g., /evaluate /path/to/plan.md

Frequently Asked Questions about source-command-evaluate

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

FAQPage Schema
How do I automate code evaluation against a predefined specification?

You can automate code evaluation against a predefined specification by running an automated review command with your plan file path. This performs contract-based grading and adversarial reviews to ensure implementation adherence without manual checks.

What is an adversarial code review and how does it validate code quality?

An adversarial code review is a parallel validation process that challenges design assumptions and identifies potential failures in an implementation. It ensures code quality by actively trying to break the code against a predefined contract before merging into the main codebase.

How do I run contract-based testing on a codebase before merging changes?

To run contract-based testing on a codebase before merging changes, execute the evaluation command with the path to your plan file. This automatically validates the code diff against the contract and provides feedback on any specification adherence issues.

Do I need a plan file to perform automated code review?

Yes, you need a plan file to perform automated code review because it defines the contract used to grade the implementation. The evaluation process requires this plan file, along with the codebase, to execute code diffing and validation commands.

Can I use automated code review to eliminate bias in pull request evaluations?

Yes, you can use automated code review to eliminate bias in pull request evaluations by grading implementations against a predefined contract. This ensures objective quality standards are met and removes human subjectivity from the code review process.

What are the limitations of contract-based code evaluation?

The limitation of contract-based code evaluation is that it cannot review code without a predefined plan file specifying the contract. It also relies entirely on the ability to execute code diffing and validation commands, requiring access to the codebase environment.