Review

Review engineer implementation proposals against PM, architect, security, and engineer artifacts.

2|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/anderson-joyle/claude-a-team --skill review-anderson-joyle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Review
Source: https://github.com/anderson-joyle/claude-a-team/tree/main/skills/review
Command: npx skills add https://github.com/anderson-joyle/claude-a-team --skill review-anderson-joyle

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It reduces the risk of shipping incorrect, incomplete, or unsafe implementation by validating the engineer’s proposed changes against the existing artifacts before any run/execution occurs.

Core Features & Use Cases

  • Correctness & Completeness Checks: Verifies the proposal covers the requested behavior and anticipated cases without inventing evidence.
  • Risk & Testability Review: Flags weak assumptions, missing test coverage, unnecessary complexity, and inadequate risk coverage.
  • Evidence-Grounded Approval Workflow: Approves, approves with notes, or requests changes while staying strictly tied to the provided request/PM/architect/security/engineer artifacts.

Quick Start

Use the Review skill to evaluate the engineer’s implementation proposal and decide whether it is approved, needs changes, or should be held based on the available artifacts.

Frequently Asked Questions about Review

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

FAQPage Schema
How do I validate an engineer's implementation proposal before pipeline execution?

To validate an implementation proposal before execution, perform a second-opinion review assessing correctness, completeness, testability, and risk coverage against existing PM, Architect, and Security artifacts.

What is an evidence-grounded approval workflow for software engineering artifacts?

An evidence-grounded approval workflow evaluates engineer artifacts strictly against provided request and security documents, deciding whether to approve, approve with notes, or request changes without fabricating execution evidence.

How do I review testability and risk coverage in a proposed software change?

Review testability and risk coverage by flagging weak assumptions, missing test coverage, unnecessary complexity, and inadequate risk mitigation found within the engineer's proposed implementation artifacts.

Can I use artifact validation to prevent unsafe code execution in a software pipeline?

Yes, artifact validation prevents unsafe code execution by assessing engineer proposals against parent artifacts for correctness and risk coverage, producing a review output that must be checked before any run occurs.

What is the best way to check implementation completeness without inventing evidence?

The best way to check implementation completeness without inventing evidence is to validate the proposed changes strictly against existing PM and Architect artifacts, ensuring requested behavior is covered without fabrication.

Why does my approval workflow need a preserved request_id and schema_version?

Your approval workflow needs a preserved request_id and schema_version to maintain traceability within the shared artifact envelope, ensuring the review output explicitly links back to the correct parent artifacts.