requesting-code-review

Dispatch a code-reviewer subagent to validate completed work against requirements.

2|1|Updated May 1, 2026
One-click install
npx skills add https://github.com/LeonardoTan19/metaforge --skill requesting-code-review-leonardotan19
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/LeonardoTan19/metaforge/tree/main/skills/requesting-code-review
Command: npx skills add https://github.com/LeonardoTan19/metaforge --skill requesting-code-review-leonardotan19

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This tool automates the critical step of validating work through a dedicated code-review subagent, ensuring issues are surfaced before they cascade into larger tasks and merges.

Core Features & Use Cases

  • Dispatch a code-reviewer subagent after each task in subagent-driven development to validate work against the plan.
  • Provide precise context (DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA) so the reviewer evaluates only the work product.
  • Receive structured feedback with Strengths, Issues (Critical/Important/Minor), Recommendations, and an overall Assessment to guide next actions.
  • Use before merging to main or after major features to ensure readiness and maintain code quality.

Quick Start

Request a code review after completing a task by providing the DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, and HEAD_SHA.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I automate code review before merging to main?

Automate code review by dispatching a code-reviewer subagent to validate completed work against your requirements before merging to main. Provide the DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, and HEAD_SHA to receive structured feedback on strengths, issues, and readiness.

What is subagent-driven development code review?

Subagent-driven development code review dispatches a dedicated reviewer subagent to validate completed task work against its plan. It evaluates only the work product using precise context like BASE_SHA and HEAD_SHA, outputting a formal assessment of strengths, issues, and recommendations.

How do I validate completed tasks against requirements using automation?

Validate completed tasks against requirements by dispatching a code-reviewer subagent with a structured prompt including DESCRIPTION and PLAN_OR_REQUIREMENTS. The subagent compares the work product against the plan and outputs a formal review with critical issues and an overall readiness assessment.

Can I use a subagent to catch code issues after major feature completion?

Yes, you can use a subagent to catch code issues after major feature completion. Dispatch the code-reviewer with the BASE_SHA and HEAD_SHA of the new work to surface issues of varying severity, ensuring overall readiness and maintaining code quality before proceeding.

What context do I need to provide for automated code review?

Automated code review requires a structured prompt containing DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, and HEAD_SHA. This precise context ensures the reviewer subagent evaluates only the specified work product and outputs accurate strengths, issues, recommendations, and an overall assessment.

Does automated code review output a formal readiness assessment?

Yes, automated code review outputs a formal readiness assessment. Alongside strengths, issues categorized by severity, and recommendations, the subagent provides an overall assessment to guide your next actions and determine if the work is ready to merge.