Error Debugging Multi Agent Review

This orchestrates multiple specialized AI agents to review code from different angles at once. You feed it a file path, repo, or snippet, and it routes the work to agents handling security, performance, architecture, compliance, and more. The coordination logic is smart: some agents run in parallel, others sequentially when they need each other's insights, then everything gets synthesized into a unified report with conflict resolution. It's overkill for quick fixes but makes sense when you need comprehensive coverage across domains and don't want to manually coordinate separate review passes. The plugin architecture means you can add custom agent types as your needs evolve.

skills.sh installs: 319
GitHub stars: 39.4K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill error-debugging-multi-agent-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Compatibility and maintenance

Primary editorial path for this compatibility group. The full instructions and support files remain local so existing installations continue to work offline. This is one shared procedure, not an additional capability. Preserve the callable ID when an existing manifest or client configuration uses it. Modified in AAS on 2026-09-05; original metadata and license notices are retained.

Coordinate a bounded code review

When to Use

Review a defined diff or subsystem from several relevant perspectives, such as correctness, authorization and performance. The skill describes a review procedure; it does not install an orchestration engine or prove compliance.

Inputs and execution scope

Pin repository/base/head, the changed paths, intended behavior and available tests. Use independent agents only if the user authorizes delegation and the host supports it. Otherwise conduct the perspectives sequentially. Do not spawn agents merely because this callable ID contains “multi-agent”. Read-only review is the default; fixes, external posts and deployment stay within the user's actual task authority.

SKILL.md on GitHub