full-review

Coordinate gated multi-dimensional code review across git scopes with verified synthesis.

Updated May 10, 2026
One-click install
npx skills add https://github.com/rob-broadley/ai-airbase --skill full-review-rob-broadley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: full-review
Source: https://github.com/rob-broadley/ai-airbase/tree/main/cadre/skills/full-review
Command: npx skills add https://github.com/rob-broadley/ai-airbase --skill full-review-rob-broadley

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps teams quickly validate software quality by orchestrating a complete, multi-dimensional review with a clear scope gate and a standardized output.

Core Features & Use Cases

  • Comprehensive, multi-agent review: Coordinates specialists for testing, security, API quality, error handling, observability, dependencies, documentation, concurrency, and dead code.
  • Deterministic pre-flight readiness: Verifies required tools and bootstraps missing analysis tooling before dispatching reviewers.
  • Verified, structured synthesis: Merges findings by severity, verifies file/location references, and outputs a single consolidated report.

Quick Start

Ask the AI to run a comprehensive full review of the current project, using the latest scope if no git ref is provided, and include a final merged report in the standard severity format.

Frequently Asked Questions about full-review

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

FAQPage Schema
How do I run a comprehensive code review across my entire git diff?

Run a comprehensive code review by resolving a Git scope such as a commit range or branch diff. The review coordinates parallel specialists across testing, security, API design, error handling, and concurrency, then merges findings into a single severity-tiered report.

What does static analysis cover in a multi-agent code review?

Static analysis in this review covers test coverage, security vulnerabilities, API design, error handling, observability, dependency risk, documentation, concurrency, and dead code detection. Each dimension is handled by a specialist agent before results are synthesized.

Can I use this code review on a specific git commit range instead of the whole codebase?

Yes, you can target a specific git commit range or codebase scope. The review requires explicit user confirmation of the resolved Git scope before dispatching parallel specialist agents, ensuring analysis is scoped to your chosen changes.

Do I need to install analysis tools before running a gated code review?

No, pre-flight readiness checks verify required tools and optionally bootstrap missing analysis tooling before dispatching reviewers. This ensures the environment is prepared automatically without manual setup.

How are code review findings verified and reported?

Findings are merged by severity tiers and verified to ensure any cited file or line location exists and matches the reported issue. The final output is a consolidated report with verified, structured synthesis across all review dimensions.

What's the best way to detect dead code and concurrency issues in my project?

A gated code review dispatches specialist agents to analyze concurrency and dead code alongside security, testing, and documentation. Results are merged into a single severity-tiered report with verified file and line references.