How does the Code Reviewer handle subjective 'nitpicks'?

The skill uses a strict confidence scoring system. Only issues with a certainty score of 80% or higher are reported, ensuring that feedback is objective and impactful rather than speculative.

How does it decide whether to approve or request changes?

Approval is granted when all verification checks pass and business logic is sound. Changes are requested for critical issues like security holes, correctness bugs, or missing tests.

What dimensions of quality does the review cover?

It evaluates code across six specific dimensions: Correctness, Safety (Security), Maintainability, Testability, Performance, and Standards Compliance.

Does this skill report pre-existing issues in the codebase?

No, the skill includes a critical filtering rule to ignore pre-existing issues not introduced by the current change, focusing specifically on the impact of the new code.

Can I use this instead of a linter or automated test suite?

No, this skill is designed to be used after automated verification. It provides human-like reasoning for architectural and logic issues that automated tools often miss.

Code Reviewer

Name: Code Reviewer
Author: TheBushidoCollective

byTheBushidoCollective

•

协作工具

Conducts systematic, high-confidence code reviews using a structured multi-dimensional evaluation process to ensure software quality.

关于

The Code Reviewer skill provides a rigorous framework for evaluating code changes across critical dimensions including correctness, safety, maintainability, and performance. By implementing a strict confidence-scoring system—reporting only issues with at least 80% certainty—it eliminates noise and pedantic 'nitpicking,' focusing instead on actionable, high-impact feedback. This skill streamlines the verification phase of development by providing structured summaries, positive reinforcement of strengths, and clear approval decisions based on professional software engineering standards and the Boy Scout Rule.

主要功能

Defined approval criteria and red-flag detection for immediate security risks
Strict 80%+ confidence threshold to minimize review noise and false positives
Multi-dimensional quality assessment covering safety, logic, and maintainability
Pre-review context gathering via git diff and codebase grepping
39 GitHub stars
Structured feedback reports with severity levels and actionable fixes

使用场景

Pre-merge safety auditing for sensitive logic or infrastructure changes
Automating peer review workflows to ensure consistent quality standards
Standardizing feedback across teams to focus on objective architectural issues

关于

主要功能

Defined approval criteria and red-flag detection for immediate security risks
Strict 80%+ confidence threshold to minimize review noise and false positives
Multi-dimensional quality assessment covering safety, logic, and maintainability
Pre-review context gathering via git diff and codebase grepping
39 GitHub stars
Structured feedback reports with severity levels and actionable fixes

使用场景

Pre-merge safety auditing for sensitive logic or infrastructure changes
Automating peer review workflows to ensure consistent quality standards
Standardizing feedback across teams to focus on objective architectural issues