How do I trigger the AI Critic skill?

You can trigger it by asking Claude to 'address AI feedback', 'fix AI review suggestions', or 'address suggestions from pair-review'.

What happens to dismissed suggestions?

The skill only fetches active and adopted suggestions; any feedback previously dismissed in the pair-review interface is automatically excluded.

Can I use this skill on local branches without a GitHub PR?

Yes, the skill automatically detects if a PR exists. If not, it uses local mode based on your current git HEAD and directory path.

Does it support specific analysis runs?

Yes. If you want suggestions from a specific run, Claude can list available analysis runs and you can provide the specific run ID.

Does AI Critic automatically apply all suggestions?

No. The skill evaluates each suggestion to determine if it is a real issue or a false positive, applying only those it deems valid and actionable.

AI Code Review Critic

Name: AI Code Review Critic
Author: in-the-loop-labs

byin-the-loop-labs

•

コラボレーションツール

Automates the process of fetching, triaging, and applying AI-generated code review suggestions from the pair-review platform.

The AI Code Review Critic skill bridges the gap between static analysis and code implementation by allowing Claude to interact directly with the pair-review ecosystem. It automatically detects whether a project is in a local or Pull Request state, retrieves intelligent review suggestions, and applies valid fixes while filtering out false positives. This skill is designed for developers who want to accelerate their code review cycles and ensure high code quality through a seamless human-in-the-loop AI collaboration workflow.

主な機能

0116 GitHub stars

02Intelligent code modifications to resolve valid issues and stylistic suggestions

03Context-aware detection for local git branches or GitHub Pull Request environments

04Automated triaging of AI suggestions based on file content and confidence signals

05Detailed summary reporting on addressed versus skipped suggestions with reasoning

06Direct integration with pair-review MCP tools to fetch the latest analysis runs

ユースケース

01Reviewing and applying suggestions from specific historical analysis runs

02Automatically addressing feedback from AI-generated Pull Request reviews

03Iterating on local code quality based on AI analysis before pushing changes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add in-the-loop-labs/pair-review ai-critic

For use in Claude.ai and ChatGPT

Download Skill