AgentSkillsCN

requesting-code-review

在完成任务、实现重大功能，或在合并前使用此技能——通过分叉的代码审查代理运行审查流程，确保工作成果符合既定要求。

SKILL.md
--- frontmatter
name: requesting-code-review
description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements - runs review in a forked code-reviewer agent
context: fork
agent: code-reviewer

Requesting Code Review

Run code review in a forked code-reviewer agent to catch issues before they cascade.

Core principle: Review early, review often.

When to Request Review

Mandatory:

  • •After each task in agent-team-driven development
  • •After completing major feature
  • •Before merge to main

Optional but valuable:

  • •When stuck (fresh perspective)
  • •Before refactoring (baseline check)
  • •After fixing complex bug

How to Request

1. Get git SHAs (optional):

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

2. Invoke the skill:

code
/requesting-code-review

This runs in a forked code-reviewer agent context (Claude Code 2.1.0+).

Fallback (older versions): If forked skills aren’t available, spawn the agent manually with the Task tool and use requesting-code-review/code-reviewer.md as the prompt.

3. Act on feedback:

  • •Fix Critical issues immediately
  • •Fix Important issues before proceeding
  • •Note Minor issues for later
  • •Push back if reviewer is wrong (with reasoning)

Example

code
[Just completed Task 2: Add verification function]

You: Let me request code review before proceeding.

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

/requesting-code-review

[Agent returns]:
  Strengths: Clean architecture, real tests
  Issues:
    Important: Missing progress indicators
    Minor: Magic number (100) for reporting interval
  Assessment: Ready to proceed

You: [Fix progress indicators]
[Continue to Task 3]

Integration with Workflows

Agent-Team-Driven Development:

  • •Review after EACH task
  • •Catch issues before they compound
  • •Fix before moving to next task

Executing Plans:

  • •Review after each batch (3 tasks)
  • •Get feedback, apply, continue

Ad-Hoc Development:

  • •Review before merge
  • •Review when stuck

Red Flags

Never:

  • •Skip review because "it's simple"
  • •Ignore Critical issues
  • •Proceed with unfixed Important issues
  • •Argue with valid technical feedback

If reviewer wrong:

  • •Push back with technical reasoning
  • •Show code/tests that prove it works
  • •Request clarification

See template at: requesting-code-review/code-reviewer.md