ce-devils-advocate

Critique code-change proposals for hidden risks and regressions with structured ratings.

78|15|Updated May 1, 2023
One-click install
npx skills add https://github.com/Moffran/calibrated_explanations --skill ce-devils-advocate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ce-devils-advocate
Source: https://github.com/Moffran/calibrated_explanations/tree/main/.claude/skills/ce-devils-advocate
Command: npx skills add https://github.com/Moffran/calibrated_explanations --skill ce-devils-advocate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarially challenge cleanup and test proposals for hidden risk, weak evidence, and coverage or behavior regressions, including Option A/B/C focus-specific risks.

Core Features & Use Cases

  • Implements a Devil's Advocate review role to stress-test proposals against risk, evidence quality, and potential regressions.
  • Guides reviewers to consider ADR-030 prompts and related CE workflows, surfacing high-impact risks for action.
  • Supports multi-option focus analysis (A/B/C) to balance different risk dimensions.

Quick Start

Activate the Devil's Advocate review on a CE proposal and generate a risk-focused objections report following ADR-030.

Frequently Asked Questions about ce-devils-advocate

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

FAQPage Schema
How do I perform a devil's advocate review on a code cleanup proposal?

A devil's advocate review challenges code-change proposals by identifying hidden risks, weak evidence, and potential regressions across cleanup, test quality, and maintainability. You apply it to proposals from specific code evaluation workflows to ensure ADR-030 criteria are followed before execution.

What is adversarial risk analysis for code quality proposals?

Adversarial risk analysis stress-tests code cleanup and test proposals against evidence quality and potential behavior regressions. It surfaces high-impact risks for action by applying ADR-030 prompts, providing structured risk ratings and follow-up actions to prevent regressions.

How do I evaluate test pruning proposals for potential regressions?

You evaluate test pruning proposals by applying a devil's advocate review role that identifies hidden risks and coverage regressions. The process checks proposals against ADR-030 criteria and generates a risk-focused objections report with structured ratings.

Can I use this approach to review dead code removal suggestions?

Yes, you can review dead code removal suggestions by challenging the proposals for weak evidence and maintainability risks. The review applies ADR-030 prompts to surface high-impact risks and provide structured follow-up actions before execution.

What's the best way to balance different risk dimensions in code reviews?

Multi-option focus analysis (A/B/C) balances different risk dimensions by evaluating cleanup and test proposals across specific risk categories. This approach ensures comprehensive adversarial review by structuring risk ratings and follow-up actions for each focus area.

When should I not use adversarial review for code changes?

Adversarial review is specifically designed for pre-execution evaluation of cleanup, test pruning, dead code removal, and code quality proposals. It is not intended for standard feature development reviews or proposals outside the ADR-030 workflow scope.