Agent Skills › HashWarlock/nobody-plans-for-pi › nobody-receives-code-review

nobody-receives-code-review

GitHub

指导开发者在接收代码审查反馈时进行技术验证与批判性评估，而非盲目接受。提供理解、验证、评估和回应的四步法则及具体话术模板，旨在提升代码质量与沟通效率。

skills/nobody-receives-code-review/SKILL.md HashWarlock/nobody-plans-for-pi

Trigger Scenarios

收到代码审查意见需要回复评审者关于代码改动的质疑

Install

npx skills add HashWarlock/nobody-plans-for-pi --skill nobody-receives-code-review -g -y

More Options

Use without installing

npx skills use HashWarlock/nobody-plans-for-pi@nobody-receives-code-review

指定 Agent (Claude Code)

npx skills add HashWarlock/nobody-plans-for-pi --skill nobody-receives-code-review -a claude-code -g -y

安装 repo 全部 skill

npx skills add HashWarlock/nobody-plans-for-pi --all -g -y

预览 repo 内 skill

npx skills add HashWarlock/nobody-plans-for-pi --list

SKILL.md

Frontmatter

{
    "name": "nobody-receives-code-review",
    "description": "Use when receiving code review feedback, before implementing suggestions — requires technical rigor and verification, not performative agreement"
}

Receiving Code Review

Overview

Code review feedback requires critical evaluation, not blind acceptance. Verify each suggestion technically before implementing.

The Rule

For each piece of feedback:

Understand — What specifically is the concern?
Verify — Is the concern technically valid? Check the code.
Evaluate — Does the suggested fix actually address the concern?
Respond — Agree with evidence, disagree with evidence, or ask for clarification

Response Types

Agree (with evidence)

You're right — line 42 doesn't handle the null case.
Fix: added null check with test in abc123.

Disagree (with evidence)

This is actually handled by the validation in middleware.py:30
which runs before this function is called. Here's the test
that covers it: test_middleware_validates_input.

Clarify

I'm not sure I understand the concern about the retry logic.
Are you worried about the backoff strategy or the max retries?

Anti-Patterns

Bad	Good
"Good point, fixed!" (without checking)	Verify the concern, then fix
Implementing all suggestions blindly	Evaluate each on merit
Dismissing without explanation	Provide evidence for disagreement
"I'll fix it later"	Fix now or explain why not
Changing unrelated code during review	Only address review feedback