skills.rest
Gamezar
GamezarCOMMUNITY
Explore all skills by this author →
GitHub

reflexion-critique

Orchestrate multi-agent debate to review completed work and generate critique reports.

Updated Mar 10, 2026
Search Tags:#quality assurance#code review#feedback#refactoring#software development#ai judges
One-click install
npx skills add https://github.com/Gamezar/opencode-cek --skill reflexion-critique-gamezar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reflexion-critique
Source: https://github.com/Gamezar/opencode-cek/tree/main/plugins/reflexion/skills/reflexion-critique
Command: npx skills add https://github.com/Gamezar/opencode-cek --skill reflexion-critique-gamezar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of getting comprehensive, multi-faceted feedback on completed work, ensuring quality, alignment, and identifying areas for improvement.

Core Features & Use Cases

  • Automated Multi-Agent Review: Orchestrates specialized AI judges (Requirements Validator, Solution Architect, Code Quality Reviewer) to provide independent critiques.
  • Structured Feedback: Generates detailed reports covering requirements alignment, solution optimality, and code quality.
  • Consensus Building: Facilitates debate between judges to resolve disagreements and reach a unified assessment.
  • Use Case: After a developer completes a new feature, this Skill can be invoked to provide a thorough review, highlighting potential issues, suggesting refactors, and confirming adherence to requirements before merging.

Quick Start

Initiate a review of the recent changes in the current project.

Frequently Asked Questions about reflexion-critique

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

FAQPage Schema
How do I automate code review for a completed feature before merging?▼

Automate code review by orchestrating specialized AI judges to assess requirements alignment, solution architecture, and code quality, generating a detailed critique report with refactoring suggestions.

What is multi-perspective AI review for software development?▼

Multi-perspective AI review is a process where specialized judges independently evaluate work and use a debate-and-consensus pattern to resolve disagreements, ensuring objective and comprehensive feedback.

How does consensus building work in AI-driven code quality evaluation?▼

Consensus building in code quality evaluation facilitates a structured debate between parallel AI judges to resolve disagreements, ultimately producing a unified assessment and detailed critique.

Can I use automated AI judges to check requirements alignment and suggest refactoring?▼

Yes, automated AI judges can validate requirements alignment and generate structured feedback that highlights potential issues and suggests refactors to improve solution optimality and code quality.

What's the best way to get objective feedback on solution architecture?▼

Get objective feedback on solution architecture by utilizing parallel agent execution and structured verification processes, which independently assess architectural optimality before reaching a consensus.

Related Skills

Explore More Software Engineering Skills→
ai-native-campai-native-camp
18

session-wrap

Analyze completed coding sessions and generate commit messages with Git.

Official
Advanced
reedmayhew18reedmayhew18
23

code-review

Identify issues in code changes and produce a severity-organized report.

Community
Advanced
petrkohutpetrkohut

bmad-testarch-test-review

Automate test quality review and validation against best practices.

Community
Advanced
ahiendzahiendz
3

lint-and-validate

Lint and statically analyze Node.js/TypeScript and Python codebases.

Community
Intermediate