skills.rest
zMynxx
zMynxxCOMMUNITY
Explore all skills by this author →
GitHub

requesting-code-review

Dispatches a code reviewer subagent to evaluate git changes against requirements before merging.

Updated Jun 5, 2026
Search Tags:#code quality#code review#feedback#ai agent#subagent#merge readiness#git diff
One-click install
npx skills add https://github.com/zMynxx/bifrost-with-opencode --skill requesting-code-review-zmynxx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/zMynxx/bifrost-with-opencode/tree/main/agent/skills/requesting-code-review
Command: npx skills add https://github.com/zMynxx/bifrost-with-opencode --skill requesting-code-review-zmynxx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code written by AI agents or developers often goes unreviewed until issues compound across tasks. This Skill enforces a structured review checkpoint by dispatching a dedicated reviewer subagent with precisely scoped context, catching Critical and Important issues before they cascade into more work. ## Core Features & Use Cases - Subagent-Based Review: Dispatches a general-purpose subagent using a detailed reviewer prompt template, keeping the reviewer's context separate from your working session. - Structured Feedback Format: Returns strengths, severity-categorized issues (Critical / Important / Minor), recommendations, and a clear merge readiness verdict. - Git Range Scoping: Reviews a precise commit range using BASE_SHA and HEAD_SHA so feedback targets exactly the changes made. - Use Case: After completing a task in subagent-driven development, you capture the base and head commit SHAs, dispatch the reviewer with the task requirements, receive categorized feedback, fix Important issues, and proceed to the next task with confidence. ## Quick Start Ask the agent to request a code review of the changes between the previous commit and HEAD using the code-reviewer template before continuing to the next task.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I request a code review from an AI subagent?▼

Capture the base and head commit SHAs with git rev-parse, then dispatch a general-purpose subagent using the code-reviewer.md template. Fill in the description, requirements, and SHA placeholders so the reviewer evaluates exactly the changes made.

When should I request a code review during development?▼

Request review after each task in subagent-driven development, after completing major features, and before merging to main. It is also valuable when stuck, before refactoring, or after fixing a complex bug.

What feedback format does the code reviewer return?▼

The reviewer returns strengths, issues categorized as Critical, Important, or Minor with file:line references, recommendations, and a final assessment stating whether the work is ready to merge. Each issue explains what is wrong, why it matters, and how to fix it.

Can the code reviewer subagent modify my working tree?▼

No. The review is strictly read-only on the current checkout. The reviewer uses git show, git diff, and git log to inspect history, and must use a separate temporary worktree if it needs to examine a different revision.

What should I do if I disagree with the reviewer's feedback?▼

Push back with technical reasoning rather than accepting incorrect feedback. Show code or tests that prove the implementation works, and request clarification. However, never ignore valid Critical issues or proceed with unfixed Important ones.

Related Skills

Explore More Software Engineering Skills→
norrbackanorrbacka

requesting-code-review

Review completed code changes against requirements before merge.

Community
Intermediate
WesleyMFrederickWesleyMFrederick

requesting-code-review

Dispatch a code-reviewer subagent to review Git changes between BASE_SHA and HEAD_SHA.

Community
Basic
phraphra

code-review

Review modified code files and auto-fix mechanical issues.

Community
Advanced
Sir-chawakornSir-chawakorn
33

ai-pair-programming

Facilitate real-time collaborative pair programming sessions between a human developer and an AI.

Community
Intermediate