skills.rest
civitai
civitaiOFFICIAL
Explore all skills by this author →
Website𝕏@HelloCivitaiGitHub

agent-review

Route Anthropic models through Claude Agent SDK and others via OpenRouter for external AI feedback.

7.2k|732|Updated Oct 11, 2022
Search Tags:#architecture#openrouter#anthropic#code-review#model-routing#ai-assisted-review#external-review
One-click install
npx skills add https://github.com/civitai/civitai --skill agent-review-civitai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-review
Source: https://github.com/civitai/civitai/tree/main/.claude/skills/agent-review
Command: npx skills add https://github.com/civitai/civitai --skill agent-review-civitai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic-ai/claude-agent-sdk.

What problem does it solve?

Provide reliable external AI feedback by routing Anthropic models through Claude Agent SDK (local subscription) and other models through OpenRouter API to streamline expert reviews.

Core Features & Use Cases

  • Route AI models to suitable providers for unbiased external feedback on code, architecture, and design decisions.
  • Support including input context, file references, and selective lines to focus reviews.
  • Use cases include code reviews, architectural critiques, and design validation with expert opinions.

Quick Start

Submit your code or design prompt to receive external AI review routed through Claude Agent SDK for Anthropic models and OpenRouter for others.

Frequently Asked Questions about agent-review

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

FAQPage Schema
How do I get AI code review from external models using Claude Agent SDK?▼

You can get AI code review by routing Anthropic models through Claude Agent SDK and other models through OpenRouter. Submit code, architecture decisions, or design prompts to receive expert external feedback.

Can I review specific lines of code with OpenRouter and Anthropic models?▼

Yes, you can review selective lines of code by providing file or stdin input with optional line ranges. This focuses the external AI review on specific code segments and includes additional context.

How does model routing work for AI-assisted architecture reviews?▼

Model routing for AI-assisted architecture reviews directs Anthropic models through Claude Agent SDK using local subscriptions, while routing other models through the OpenRouter API to provide external feedback.

Can I output raw JSON from an external AI code review for pipeline integration?▼

Yes, you can output raw JSON from the external AI code review. This allows you to integrate the routed model feedback directly into continuous integration pipelines or other automated systems.

Do I need an OpenRouter API key to review code with non-Anthropic models?▼

Yes, you need an OpenRouter API key to route non-Anthropic models for code review. Anthropic models are routed separately through the Claude Agent SDK using your local subscription.

Related Skills

Explore More Software Engineering Skills→
whmathews15whmathews15
1

ai-setup

Configure Dex AI model options for cost reduction and offline access.

Community
Advanced
keboolakeboola
15

codex

Invoke Codex CLI to generate structured JSON second opinions on code and architecture.

Official
Advanced
InverterNetworkInverterNetwork

requesting-code-review

Automates pre-commit code verification through static security analysis, linting, and independent review.

Official
Advanced
warpdotdevwarpdotdev
292

update-pr-review

Aggregate pull request review threads to update local SKILL.md files.

Official
Advanced