An AI agent can ask this skill to gather the right reviewers for a code change or a plan document. It looks at the files and keywords to pick experts like a code reviewer, security auditor, or design reviewer. The skill also sets rules for how many review rounds are allowed and when to stop or escalate.
This keeps the review process consistent and fair. Every review has a clear gate and cap so teams never get stuck in endless loops. The orchestrator agent uses the panel and policy to run the review smoothly.
Teams that follow a structured review workflow will find this skill very helpful. It saves time by automatically choosing reviewers based on the type of work and previous findings.
Global
mkdir -p ~/.claude/skills/assemble-panelProject
mkdir -p .claude/skills/assemble-panelImprove Codebase Architecturemattpocock/skills
Scan your codebase for architecture improvements with visual reports and pick one to refactor
Web Design Guidelinesvercel-labs/agent-skills
Review your UI code for compliance with web interface guidelines
Caveman Reviewjuliusbrussee/caveman
Ultra-compressed one-line code review comments that cut noise
Zoom Outmattpocock/skills
Get a big picture view of your code with a simple map of modules and callers
Codebase Designmattpocock/skills
Create deep modules with tiny interfaces and lots of hidden logic for testability
Requesting Code Reviewobra/superpowers
Catch code issues early with focused automated reviews before every merge
Request Refactor Planmattpocock/skills
Plan safe code refactors with tiny commits and clear GitHub issues
Receiving Code Reviewobra/superpowers
Think first, then code. Verify feedback before making changes. Stay objective