deep-review

Review code changes for confirmed defects and regressions using verification-first methodology.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/skylarsabo/code-ops --skill deep-review-skylarsabo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/skylarsabo/code-ops/tree/main/plugins/rigor/skills/deep-review
Command: npx skills add https://github.com/skylarsabo/code-ops --skill deep-review-skylarsabo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill ensures that only confirmed defects and regressions are blocked during the code review process, providing a high-rigor verification bar for changes.

Core Features & Use Cases

  • Verification-First Methodology: Utilizes evidence tiers, disconfirmation passes, and root-cause analysis.
  • Review Output: Provides tiered comments with file:line anchors and a calibrated verdict.
  • Use Case: When reviewing a pull request, use this Skill to confirm defects and regressions before merging.

Quick Start

Run the deep-review skill on the pull request using /rigor:deep-review.

Frequently Asked Questions about deep-review

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

FAQPage Schema
How do I verify confirmed defects and regressions before merging a pull request?

A verification-first code review applies evidence tiers, disconfirmation passes, and root-cause analysis to distinguish confirmed defects from false positives. It requires executing tests and analysis tools to verify code changes before providing a calibrated merge verdict.

How do I perform a high-rigor code review that blocks only on confirmed issues?

Perform a high-rigor code review by executing tests and analysis tools to verify changes, applying disconfirmation passes and root-cause analysis. The output provides tiered comments with file:line anchors and a calibrated verdict to block only confirmed defects.

Can I use this verification-first methodology for high-stakes code reviews?

Yes, this verification-first methodology is designed for high-stakes code reviews where only confirmed defects are blocked. It requires executing tests and analysis tools to verify changes before providing a calibrated verdict with tiered comments.

What is the best way to defect detection in pull requests without blocking false positives?

Apply a verification-first methodology with evidence tiers and disconfirmation passes to detect defects without blocking false positives. This ensures only confirmed defects and regressions block merging by requiring test execution to verify changes.

Do I need to execute tests and analysis tools to verify code changes during review?

Yes, you must execute tests and analysis tools to verify code changes during review. This verification-first methodology requires test execution to apply evidence tiers and root-cause analysis for confirming defects and regressions.