← 返回 Skills 市场
Receiving Code Review
作者
lovemymobilewebsite-dotcom
· GitHub ↗
· v0.1.0
· MIT-0
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install receiving-code-review-2
功能描述
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technic...
安全使用建议
This skill is largely coherent: it gives a pattern for how to process code review feedback and how to push back or implement changes. Before installing, check the runtime context: will the agent have read/write access to your repository or the ability to post GitHub comments? The SKILL.md expects the agent to read/grep the codebase and reply in threads, but it does not declare any required credentials—make sure you understand and control the agent's repository and GitHub permissions. Also note minor oddities (references to external docs like CLAUDE.md and a prohibition on common polite phrases) that are unusual but not inherently malicious. If you allow this skill, consider restricting it to read-only mode or requiring explicit confirmation for any code modifications or external posts.
功能分析
Type: OpenClaw Skill
Name: receiving-code-review-2
Version: 0.1.0
The skill bundle contains behavioral instructions (SKILL.md) for an AI agent to handle code review feedback with technical rigor. It emphasizes verification, skepticism of external reviewers, and the avoidance of performative social responses (e.g., forbidding 'thanks' or 'great point'). The instructions include functional guidance for using the GitHub CLI (`gh api`) to reply to PR comments and using `grep` for YAGNI checks. No malicious code, data exfiltration, or harmful prompt injection attempts were identified.
能力评估
Purpose & Capability
Name and description match the SKILL.md content: the document is a step-by-step pattern for receiving and acting on code review. There are no unrelated required binaries, env vars, or installs declared.
Instruction Scope
The instructions appropriately direct the agent to read, verify against the codebase (e.g., 'grep codebase', 'check: breaks existing functionality'), and reply to reviewers (including GitHub thread guidance). These are in-scope for a code-review reception skill, but they grant the agent broad discretion to read and modify repository files and post replies. The SKILL.md also references external artifacts (e.g., 'CLAUDE.md', 'your human partner's rule') which aren't included or explained, creating ambiguity about expected behavior and policy.
Install Mechanism
No install spec and no code files — lowest-risk delivery. Nothing is written to disk by the skill itself.
Credentials
The SKILL.md instructs actions that commonly require credentials or platform access (replying in GitHub threads, modifying code, grepping the codebase, running tests), yet the skill declares no required env vars, tokens, or config paths. This mismatch is notable: either the skill expects the host agent to already have repository and GitHub access (reasonable), or it's relying on undocumented permissions. The skill does not request or document which credentials or scopes it will need, which reduces transparency about its runtime privileges.
Persistence & Privilege
always is false and there is no installation/persistent component. However, the SKILL.md repeatedly emphasizes 'just start working' and 'skip to action', which—combined with normal autonomous invocation—means an agent could autonomously make repo changes or post reviewer replies if the agent runtime permits these actions. Autonomous invocation itself is normal, but you should confirm the agent's runtime permissions before enabling this skill.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install receiving-code-review-2 - 安装完成后，直接呼叫该 Skill 的名称或使用
/receiving-code-review-2触发 - 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
v0.1.0
- Initial release of receiving-code-review skill.
- Outlines a structured, technically rigorous approach to handling code review feedback.
- Emphasizes verifying and understanding feedback before implementing changes.
- Prohibits performative agreement (no empty praise or gratitude responses).
- Provides clear procedures for unclear items, pushback, and acknowledging corrections.
- Includes real-world examples and specific guidelines for responding to both trusted and external reviewers.
元数据
常见问题
Receiving Code Review 是什么？
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technic... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。
如何安装 Receiving Code Review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install receiving-code-review-2」即可一键安装，无需额外配置。
Receiving Code Review 是免费的吗？
是的，Receiving Code Review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Receiving Code Review 支持哪些平台？
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 Receiving Code Review？
由 lovemymobilewebsite-dotcom（@lovemymobilewebsite-dotcom）开发并维护，当前版本 v0.1.0。
推荐 Skills