skills.rest
whichguy
whichguyCOMMUNITY
Explore all skills by this author →
GitHub

multi-model-code-review

Automate iterative code reviews across multiple LLM models.

1|Updated Jun 23, 2026
Search Tags:#code review#LLM#test coverage#architectural analysis#bug detection
One-click install
npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill multi-model-code-review-whichguy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: multi-model-code-review
Source: https://github.com/whichguy/hermes-skills-marketplace/tree/main/skills/multi-model-code-review
Command: npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill multi-model-code-review-whichguy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates iterative code reviews using multiple LLM subagents to identify bugs, test coverage gaps, and architectural issues.

Core Features & Use Cases

  • Multi-Model Review: Utilizes Kimi and Deepseek for comprehensive structural, logic, edge-case, and gap analysis.
  • QA Fix Workflow: Streamlines the review process with a structured QA fix workflow for efficient code improvement.
  • Fallback Pipeline: Offers a fallback delegate_task pipeline for large or multi-model reviews.
  • Dual-Review Cross-Validation: Enhances confidence by using parallel dual-review + cross-validation.
  • Dispatch Pattern: Provides guidance on dispatch patterns for single-review and batch reviews with model overrides.

Quick Start

Run the multi-model-code-review skill on your codebase by executing the command 'hermes skills execute multi-model-code-review'.

Frequently Asked Questions about multi-model-code-review

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

FAQPage Schema
How do I automate code review to find bugs and test coverage gaps?▼

Multi-model code review automates iterative bug detection and test coverage gap analysis using LLM subagents. It leverages models like Kimi and Deepseek to perform structural, logic, and edge-case analysis across your codebase.

What is the best way to run multi-model code reviews on a large codebase?▼

For large codebases, a fallback delegate_task pipeline handles multi-model reviews. This dispatch pattern supports batch reviews with model overrides, streamlining the QA fix workflow for efficient code improvement.

Does multi-model code review support cross-validation for bug detection?▼

Yes, dual-review cross-validation enhances bug detection confidence. It uses parallel reviews across multiple LLMs to cross-check structural, logic, and edge-case issues, ensuring comprehensive analysis and gap identification.

Do I need Python scripting to automate iterative code reviews?▼

Yes, Python scripting and LLM integration are required to automate iterative code reviews. The skill executes review operations on your codebase by running Python scripts via the hermes command line interface.

Can I use different LLMs for single-review and batch reviews?▼

Yes, the dispatch pattern provides guidance for single-review and batch reviews with model overrides. You can utilize Kimi and Deepseek to conduct iterative structural, logic, and edge-case analysis tailored to your workflow.

Related Skills

Explore More Software Engineering Skills→
Michae2xlMichae2xl

python-executor

Execute Python code in a secure sandboxed environment with pre-installed libraries.

Community
Advanced
LuminairPrimeLuminairPrime
1

pytest-coverage

Run pytest with coverage and generate annotated reports of untested lines.

Community
Intermediate
bobmatnycbobmatnyc
146

Requesting Code Review

Dispatch a code-reviewer subagent to review changes against plans and requirements.

Community
Basic
Marshall-HallenbeckMarshall-Hallenbeck
5

codex-review

Coordinate Codex and Claude review cycles to verify source code changes.

Community
Advanced