← 返回 Skills 市场
demo112

Superpowers Receiving Code Review

作者 demo112 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
162
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install superpowers-receiving-code-review
功能描述
Use when receiving code review feedback to verify, clarify, and evaluate technical correctness before implementing or responding, avoiding performative agree...
使用说明 (SKILL.md)

\x3C!-- Original: https://github.com/obra/superpowers, MIT License -->

name: superpowers-receiving-code-review description: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable version: 1.0.0

Code Review Reception

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.

The Response Pattern

WHEN receiving code review feedback:

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each

Forbidden Responses

NEVER:

  • "You're absolutely right!" (performative sycophancy)
  • "Great point!" / "Excellent feedback!" (performative)
  • "Let me implement that now" (before verification)

INSTEAD:

  • Restate the technical requirement
  • Ask clarifying questions
  • Push back with technical reasoning if wrong
  • Just start working (actions > words)

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not implement anything yet
  ASK for clarification on unclear items

WHY: Items may be related. Partial understanding = wrong implementation.

Example:

Cooper: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.

❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."

Source-Specific Handling

From Cooper

  • Trusted — implement after understanding
  • Still ask if scope unclear
  • No performative agreement
  • Skip to action or technical acknowledgment

From External Reviewers

BEFORE implementing:

  1. Check: Technically correct for THIS codebase?
  2. Check: Breaks existing functionality?
  3. Check: Reason for current implementation?
  4. Check: Works on all platforms/versions?
  5. Check: Does reviewer understand full context?

IF suggestion seems wrong: Push back with technical reasoning

IF can't easily verify: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

IF conflicts with Cooper's prior decisions: Stop and discuss with Cooper first

YAGNI Check for "Professional" Features

IF reviewer suggests "implementing properly":
  grep codebase for actual usage

  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
  IF used: Then implement properly

Implementation Order

FOR multi-item feedback:
  1. Clarify anything unclear FIRST
  2. Then implement in this order:
     - Blocking issues (breaks, security)
     - Simple fixes (typos, imports)
     - Complex fixes (refactoring, logic)
  3. Test each fix individually
  4. Verify no regressions

When To Push Back

Push back when:

  • Suggestion breaks existing functionality
  • Reviewer lacks full context
  • Violates YAGNI (unused feature)
  • Technically incorrect for this stack
  • Legacy/compatibility reasons exist
  • Conflicts with Cooper's architectural decisions

How to push back:

  • Use technical reasoning, not defensiveness
  • Ask specific questions
  • Reference working tests/code
  • Involve Cooper if architectural

Acknowledging Correct Feedback

When feedback IS correct:

✅ "Fixed. [Brief description of what changed]"
✅ "Good catch - [specific issue]. Fixed in [location]."
✅ [Just fix it and show in the code]

❌ "You're absolutely right!"
❌ "Great point!"
❌ "Thanks for catching that!"
❌ "Thanks for [anything]"
❌ ANY gratitude expression

Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.

If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

Gracefully Correcting Your Pushback

If you pushed back and were wrong:

✅ "You were right - I checked [X] and it does [Y]. Implementing now."
✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

❌ Long apology
❌ Defending why you pushed back
❌ Over-explaining

State the correction factually and move on.

Common Mistakes

Mistake Fix
Performative agreement State requirement or just act
Blind implementation Verify against codebase first
Batch without testing One at a time, test each
Assuming reviewer is right Check if breaks things
Avoiding pushback Technical correctness > comfort
Partial implementation Clarify all items first
Can't verify, proceed anyway State limitation, ask for direction

GitHub Thread Replies

When replying to inline review comments on GitHub, reply in the comment thread, not as a top-level PR comment.

The Bottom Line

External feedback = suggestions to evaluate, not orders to follow.

Verify. Question. Then implement.

No performative agreement. Technical rigor always.

安全使用建议
This skill is coherent and appears safe in isolation. Before installing, confirm the agent's permissions: it will sensibly need access to your repository or code files to perform the suggested verifications, and (if your platform allows autonomous invocation) you may want to restrict automatic runs so the agent doesn't post replies or make changes without human review. If you have strict data governance, run it in a workspace that has only the repositories you intend it to access.
功能分析
Type: OpenClaw Skill Name: superpowers-receiving-code-review Version: 1.0.0 The skill bundle contains instructions for an AI agent on how to handle code review feedback, emphasizing technical rigor and direct communication over social politeness. The instructions in SKILL.md are behavioral guidelines (e.g., avoiding performative gratitude, verifying feedback against the codebase, and prioritizing technical correctness) that align with the stated purpose of the skill. There is no evidence of malicious code, data exfiltration, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description match the content: the SKILL.md is a code-review reception playbook. Its recommended actions (verify against the codebase, ask clarifying questions, push back technically) are appropriate for the stated purpose.
Instruction Scope
Instructions stay within the scope of receiving and evaluating code review feedback. The doc tells the agent/human to read feedback, check the codebase (e.g., grep), verify behaviour, and respond — all expected for this purpose. There is no instruction to read unrelated system files or exfiltrate data.
Install Mechanism
No install spec and no code files; the skill is instruction-only, so nothing is written to disk and no external packages or downloads are required.
Credentials
The skill declares no environment variables, credentials, or config paths. The few implied requirements (access to the repository/codebase to verify suggestions) are proportional and consistent with the described purpose.
Persistence & Privilege
always is false and there are no actions that alter other skills or system-wide settings. Note: the platform default allows autonomous invocation, which is normal; this skill does not request elevated persistence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install superpowers-receiving-code-review
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /superpowers-receiving-code-review 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the skill for receiving and handling code review feedback. - Emphasizes technical validation over social or performative responses. - Provides a clear step-by-step response pattern before implementing review suggestions. - Details how to handle unclear or technically questionable feedback, with specific examples. - Distinguishes responses and process for trusted vs. external reviewers. - Outlines correct acknowledgement practices, prioritizing action and clarity over gratitude. - Lists common mistakes to avoid and best practices for responding to code reviews.
元数据
Slug superpowers-receiving-code-review
版本 1.0.0
许可证 MIT-0
累计安装 3
当前安装数 3
历史版本数 1
常见问题

Superpowers Receiving Code Review 是什么?

Use when receiving code review feedback to verify, clarify, and evaluate technical correctness before implementing or responding, avoiding performative agree... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 162 次。

如何安装 Superpowers Receiving Code Review?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install superpowers-receiving-code-review」即可一键安装,无需额外配置。

Superpowers Receiving Code Review 是免费的吗?

是的,Superpowers Receiving Code Review 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Superpowers Receiving Code Review 支持哪些平台?

Superpowers Receiving Code Review 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Superpowers Receiving Code Review?

由 demo112(@demo112)开发并维护,当前版本 v1.0.0。

💬 留言讨论