code-review-all

Coordinate parallel subagent reviews and synthesize severity-grouped findings into one verdict.

5|Updated Mar 24, 2026

Search Tags:#quality assurance #code review #subagents #orchestration #pull requests #repository analysis

Ready to run

npx skills add https://github.com/ably/ably-ai-transport-js --skill code-review-all

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-review-all
Source: https://github.com/ably/ably-ai-transport-js/tree/main/.claude/skills/code-review-all
Command: npx skills add https://github.com/ably/ably-ai-transport-js --skill code-review-all

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the need to run separate review passes for every concern by coordinating a full, consistent code review across multiple specialized checks and combining the results into one report.

Core Features & Use Cases

Parallel Concern Coverage: Runs focused reviews for correctness, tests, logging, docs, rules, and other project-specific concerns.
Shared Base Resolution: Resolves the comparison base once so every sub-review evaluates the same change scope.
Synthesis Into One Report: Merges findings into a single severity-grouped summary with one final verdict.
Use Case: A reviewer opens a pull request and needs a complete, read-only assessment of quality, policy conformance, and regressions without manually coordinating multiple review passes.

Quick Start

Use the code-review-all skill to review the current change against the appropriate base and return one consolidated report.

Frequently Asked Questions about code-review-all

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

FAQPage Schema

How do I run a comprehensive code review across multiple concerns in a pull request?▼

Run a comprehensive code review across a pull request by coordinating focused subagent reviews for correctness, tests, logging, docs, and rules in parallel. The system resolves a shared base branch once and synthesizes severity-grouped findings into a single verdict.

What is the best way to consolidate findings from multiple quality checks on staged diffs?▼

Consolidate findings from multiple quality checks on staged diffs by merging results into a single severity-grouped summary. This eliminates the need to run separate review passes for every concern, producing one final verdict instead of fragmented reports.

Can I review repository scopes for regressions and policy conformance without manual coordination?▼

Yes, you can review repository scopes for regressions and policy conformance without manual coordination. The skill coordinates focused sub-reviews across project-specific concerns, evaluating the same change scope against a resolved comparison base.

Does the code review orchestration apply to both staged diffs and full repository scopes?▼

Yes, the code review orchestration applies to staged diffs, pull requests, and full repository scopes. It resolves the comparison base once so every focused sub-review evaluates the same change scope consistently.

Why does a parallel code review use a shared base branch resolution?▼

A parallel code review uses shared base branch resolution to ensure every sub-review evaluates the exact same change scope. This consistency prevents mismatched findings and allows results to be synthesized into one severity-grouped report without scope drift.

What limitations exist when synthesizing a consolidated code review verdict?▼

The synthesis provides a read-only assessment of quality, policy conformance, and regressions. It is limited to analyzing the resolved change scope, meaning unchecked concerns outside the subagent coverage or base branch comparison will not appear in the final verdict.