spec-requesting-code-review

Original：🇨🇳 Chinese

Translated

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

5installs

Sourcezixun-github/aisdlc

Added on2026-02-26

NPX Install

npx skill4agent add zixun-github/aisdlc spec-requesting-code-review

SKILL.md Content (Chinese)

View Translation Comparison →

Request Code Review

Dispatch the code-reviewer subagent to catch issues before they spread.

Core Principles: Review early, review often.

Announce at the start: "I am using the spec-requesting-code-review skill to request a code review and dispatch the review subagent."

When to Request a Review

Mandatory:

After each task in subagent-driven development
After completing major features
Before merging to main

Optional but Valuable:

When stuck (for a fresh perspective)
Before refactoring (baseline check)
After fixing complex bugs

How to Request a Review

1. Get git SHAs:

bash

BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
HEAD_SHA=$(git rev-parse HEAD)

2. Dispatch the code-reviewer subagent:

Use the Task tool, with type code-reviewer, and fill in the template from

code-reviewer.md

Placeholders:

```
{WHAT_WAS_IMPLEMENTED}
```
- What you just implemented
```
{PLAN_OR_REQUIREMENTS}
```
- What should be implemented
```
{BASE_SHA}
```
- Starting commit
```
{HEAD_SHA}
```
- Ending commit
```
{DESCRIPTION}
```
- Brief summary

3. Act on Feedback:

Fix Critical issues immediately
Fix Important issues before proceeding
Record Minor issues for later handling
Object if the reviewer is wrong (with reasoning)

Example

[Just completed Task 2: Add validation functions]

You: Request a code review before proceeding.

BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)

[Dispatch code-reviewer subagent]
  WHAT_WAS_IMPLEMENTED: Session index verification and repair functions
  PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
  BASE_SHA: a7981ec
  HEAD_SHA: 3df7661
  DESCRIPTION: Added verifyIndex() and repairIndex(), covering 4 issue types

[Subagent returns]:
  Pros: Clear architecture, has real tests
  Issues:
    Important: Missing progress indication
    Minor: Magic number (100) in report interval
  Assessment: Can proceed

You: [Fix progress indication]
[Proceed to Task 3]

Integration with Workflows

Subagent-Driven Development:

Review after each task
Catch issues before they accumulate
Fix before moving to the next task

Executing Plans:

Review after every batch (3 tasks)
Get feedback, apply it, and continue

Ad Hoc Development:

Review before merging
Review when stuck

Red Flags

Never:

Skip review because it's "too simple"
Ignore Critical issues
Proceed with unresolved Important issues
Argue against valid technical feedback

If the reviewer is wrong:

Object with technical reasoning
Show code/tests that prove it works
Ask for clarification

Template located at: spec-requesting-code-review/code-reviewer.md