Does it support reviewing only the changes in a pull request?

Absolutely. It supports a git-diff format, allowing the skill to analyze only the specific lines changed rather than scanning entire files unnecessarily.

Can I focus the review on specific areas like security?

Yes, you can use the rubric-focus parameter to direct the council's attention toward specific dimensions such as Security, Performance, or maintainability.

What kind of feedback format should I expect?

The skill returns a structured JSON object containing a pass/fail verdict, a confidence score, specific rubric breakdowns, and a list of blocking issues with file and line references.

How does Council Code Review differ from standard AI reviews?

Unlike single-model tools, it uses a multi-model 'council' approach to aggregate different AI perspectives, which reduces individual model bias and provides a more reliable, structured consensus.

Council Code Review

Name: Council Code Review
Author: amiable-dev

byamiable-dev

•

Herramientas de Colaboración

Performs multi-model code reviews using structured peer evaluation to provide high-confidence feedback on pull requests and code quality.

Acerca de

The Council Code Review skill implements a sophisticated multi-model evaluation system to provide objective, structured feedback on code changes. By utilizing the LLM Council framework, it assesses implementations against specific dimensions like accuracy, clarity, and completeness, offering a more reliable analysis than single-model reviews. This skill is designed for engineering teams that require rigorous quality gates, helping to identify major blocking issues and architectural flaws through automated audits that integrate directly into the development workflow.

Características Principales

Structured scoring based on accuracy, completeness, clarity, and relevance
1 GitHub stars
Customizable rubric focus for specialized reviews like security or performance
Multi-model peer evaluation for unbiased, high-confidence feedback
Automated identification of major and minor blocking issues with line-level detail
Support for both full file analysis and change-focused git diffs

Casos de Uso

Conducting deep-dive audits on sensitive code paths like authentication or data processing
Automating pull request reviews to ensure standards are met before merging
Validating complex logic changes against a weighted accuracy and clarity rubric

Acerca de

Características Principales

Structured scoring based on accuracy, completeness, clarity, and relevance
1 GitHub stars
Customizable rubric focus for specialized reviews like security or performance
Multi-model peer evaluation for unbiased, high-confidence feedback
Automated identification of major and minor blocking issues with line-level detail
Support for both full file analysis and change-focused git diffs

Casos de Uso

Conducting deep-dive audits on sensitive code paths like authentication or data processing
Automating pull request reviews to ensure standards are met before merging
Validating complex logic changes against a weighted accuracy and clarity rubric