skills.rest
SpiralCloudOmega
SpiralCloudOmegaCOMMUNITY
Explore all skills by this author →
GitHub

Omega Critique

Automates anonymous multi-agent code-artifact review with consensus scoring and remediation guidance.

1|Updated Nov 24, 2025
Search Tags:#code-review#rubrics#security-audit#architecture-review#peer-review#llm-council
One-click install
npx skills add https://github.com/SpiralCloudOmega/DevTeam6 --skill omega-critique
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Omega Critique
Source: https://github.com/SpiralCloudOmega/DevTeam6/tree/main/.github/omega/skills/omega-critique
Command: npx skills add https://github.com/SpiralCloudOmega/DevTeam6 --skill omega-critique

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Facilitates rigorous, unbiased evaluation of software artifacts by distributing reviews across anonymous expert agents, ensuring issues are surfaced with remediation.

Core Features & Use Cases

  • Anonymous multi-agent critique: independent reviews by multiple agents, reducing bias.
  • Quorum-based decision making: findings pass only when consensus criteria are met, with remediation required.
  • Structured outputs: standardized findings, scores, and remediation guidance for easy integration into workflows.

Quick Start

Submit an artifact for review and obtain a structured set of findings through the Omega Critique workflow.

Frequently Asked Questions about Omega Critique

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

FAQPage Schema
What is anonymous multi-agent code review and how does it reduce bias?▼

Anonymous multi-agent code review distributes artifact evaluation across independent LLM agents. This peer-review mechanism ensures agents assess artifacts without mutual influence, reducing bias and surfacing issues with required remediation.

How do I automate peer-review workflows for security audits and architecture reviews?▼

Automate peer-review workflows by submitting software artifacts to an LLM council. The system applies configurable rubrics and quorum-based decision making to generate structured findings, scores, and remediation guidance.

Can I configure quorum and rubrics for consensus-based code reviews?▼

Yes, you can configure quorum and rubrics for consensus-based code reviews. The multi-agent critique workflow enforces these consensus criteria, ensuring findings pass only when quorum thresholds are met and remediation is required.

Does multi-agent LLM code review output structured findings for CI/CD integration?▼

Multi-agent LLM code review outputs standardized structured findings, scores, and remediation guidance. This standardized format is designed for easy integration into automated software engineering workflows and peer-review pipelines.

What are the limitations of using an LLM council for architecture review?▼

LLM council architecture reviews depend on quorum-based consensus, meaning valid findings lacking agent agreement may be excluded. Reviews are automated evaluations and require human verification of remediation guidance for security audits.

Related Skills

Explore More Software Engineering Skills→
indranildchandraindranildchandra
13

review-council

Compose a multi-persona advisory council to critique architecture and design decisions.

Community
Advanced
MetalLegBobMetalLegBob
11

differential-review

Analyze code changes for security risks using git history and test coverage.

Community
Advanced
eworthingeworthing

quorum-review

Coordinate multi-provider quorum reviews of AI plans to derive consensus.

Community
Advanced
EojEdredEojEdred

vote-simulation

Simulate Ëtrid governance votes with dilution algorithms, quorum rules, and role weights.

Community
Intermediate