Borrowing it
Nothing to install: this file belongs to aide-family/moon-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aide-family/moon-web/main/.cursor/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/aide-family/moon-webWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aide-family/moon-web/code-review)<a href="https://agentmods.dev/skills/aide-family/moon-web/code-review"><img src="https://agentmods.dev/badge/skills/aide-family/moon-web/code-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01548 |
| Opus 5 | $0.00032 | $0.00774 |
| Sonnet 5 | $0.00013 | $0.00310 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码审核
对当前 Git 变更 进行审核:排查潜在 bug、评估代码质量,并严格按 React 规范与 Ant Design v6 检查风格与实现。发现问题必须给出修正方案或直接修正。
触发场景
- 用户说「帮我审核当前变更」
- 用户说「帮我审核代码」
审核范围:仅针对 当前未提交的变更(git diff / staged 文件)。先获取变更内容再开始审核。
审核维度
1. 正确性与 Bug
- 逻辑是否正确,边界与空值是否处理。
- 异步请求:是否有卸载后 setState、是否缺少 loading/error 处理。
- 类型:是否滥用
any、类型断言是否合理、与 API 类型是否一致。枚举一致性:若 API 已改为枚举类型(如GlobalStatus、DatasourceType、SampleMode、ConditionMetric),则:(1)所有调用处、回调参数、setState/表单状态 均使用该枚举类型,不得遗留string/number或modeRaw/conditionRaw等原始值落库到状态;(2)提交请求参数 直接传枚举值,不得对枚举字段使用String()/Number()转换(例如mode: editingLevelData.mode而非String(editingLevelData.mode));(3)表单收集枚举字段 时用 Select + 枚举 options,勿用Input type="number"或裸字符串再转 Number。 - 依赖数组与副作用:
useEffect/useMemo/useCallback依赖是否完整、是否造成多余渲染或闭包陈旧。
2. React 规范(必须严格遵守)
- 组件:使用
React.FC<Props>或function Component(props: Props),Props 用interface明确定义。 - 类型:优先
import type,状态与 API 返回类型一致。 - Hooks:只在顶层调用,条件/循环中不调用;自定义 Hook 命名以
use开头。 - 列表 key:使用稳定、唯一标识,禁止用 index 作为 key(列表会增删重排时)。
- 受控/非受控:表单与可编辑 UI 的受控方式一致,无受控/非受控混用导致的警告或 bug。
- 参考项目内 react-antd-page 中的结构与类型、请求与状态等约定。
3. 复用与冗余(硬性要求)
- 能复用的必须复用:若变更中有与
src/components/或同项目其他模块可复用的逻辑/组件,必须改为复用,不得重复实现。 - 禁止额外创造不必要的东西:不新增重复工具函数、不新增与现有组件功能重叠的组件;若现有 API 模块(
src/api/)已有对应接口与类型,必须使用,不得在页面内重复定义请求或类型。
4. Ant Design v6 与 UI 风格(必须严格遵守)
- 仅使用 Ant Design v6 当前推荐的组件与 API,以 官方文档 为准。
- 禁止使用已弃用的组件、属性或变量(如文档标注废弃的 List 等,需改用推荐替代方案)。遇控制台弃用警告须按提示替换,例如:Divider 的
orientationMargin已废弃,须用styles.content的逻辑外边距替代——titlePlacement='left'时用styles={{ content: { marginInlineStart: 0 } }},titlePlacement='right'时用marginInlineEnd: 0(与 antd 源码中 innerStyle 一致),勿仅写margin: 0。 - Table 的
rowKey若为函数,不得使用第二个参数 index(v6 已废弃且行为不保证);须用行的稳定字段(如record.uid、record.id或组合字段)生成唯一 key。 - 按需从
antd引入组件,图标从@ant-design/icons按需引入。 - 表格列使用
ColumnsType<YourRowType>,类型与 API 的 Item/Row 一致。 - 若项目已配置
ConfigProvider/App,主题与国际化保持一致。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 69 lines · 64 tokens per session scan A 54ff6c81c585
code-review is a skill published in the GitHub repository aide-family/moon-web (12 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,548 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.