Automated summary
Performs a full-stack code review of a Rust/React application, including static analysis, edge case checks, and a prioritized report.
Strengths
- Structured priority-based approach (P0/P1/P2) to guide fixes
- Includes Rust-specific checks (unwrap, Mutex, Tauri) and React-specific ones (hooks, events)
- Offers a step to enrich internal rules by analyzing error patterns
Limitations
- Requires a Rust and Node.js environment for static analysis
- Relies on predefined rules in .claude/rules/ whose quality affects detection
- Does not automatically cover unit or integration tests
For rigorous quality assurance before merging on a Rust/React Tauri codebase.
For projects without Rust/React components or when a quick informal review is sufficient.
Security analysis
SafeThe skill uses only static analysis commands (npx tsc, cargo check) and git operations for diffs; there are no destructive actions, exfiltration, or execution of arbitrary user-provided code. The npx whitelisting is restricted to the safe tsc compiler in the given instructions.
No concerns found
How this analysis is madeExamples
Review the code changes from the last 3 commits in this full-stack Tauri project.Do a full-stack code review on the src/ directory, covering both Rust and React code.Run a full-stack code review on the current branch diff compared to main.description: 代码审查（全栈） allowed-tools: Bash(git:, cargo:, npm:, npx:), Read, Glob, Grep argument-hint: [HEAD~N | file | directory]
全栈代码审查
$ARGUMENTS
1. 确定审查范围
根据参数确定要审查的代码：
- 无参数：
git diff当前分支相对 main 的变更 HEAD~N：最近 N 次提交的变更- 文件/目录路径：指定范围
2. 执行静态分析
npx tsc --noEmit
cd src-tauri && cargo check
3. 逐文件审查（借鉴 Bugbot 策略）
核心方法论见
.claude/rules/code-review-strategy.md
对每个变更的函数/代码块，先做边界情况扫描：
[ ] 输入为空/null/undefined 时行为是否正确？
[ ] 错误路径是否会阻止后续执行（而非静默继续）？
[ ] 返回值的所有可能形态是否都被消费方处理？
[ ] 外部调用失败时是否有正确的错误传播？
[ ] 并发/重复执行时是否安全？
[ ] 状态变更是否会影响其他依赖方？
然后按优先级分类：
正确性（P0）
Rust 端:
- 逻辑错误、边界情况（空值、零值、空数组）
unwrap()panic 风险- SQL 参数化（禁止字符串拼接）
- Mutex 锁持有时间（禁止跨 await）
- Tauri 命令是否在 lib.rs 中注册
React 端:
- TypeScript 类型安全（是否有
any、类型断言） - React Hook 使用规则（条件调用、依赖数组）
- Tauri Event 监听是否在 cleanup 中取消
- 安全漏洞（硬编码凭证、XSS）
性能（P1）
- Rust: 不必要的
clone()、大数据复制 - React: 组件内定义对象/数组导致子组件重渲染
- 数据库：缺少索引、N+1 查询
useEffect依赖是否正确
代码质量（P2）
- 文件是否超过 400 行
- 命名是否清晰
- 是否符合架构（依赖方向）
- 是否有重复代码可以提取
4. 生成审查报告
以表格形式输出发现的问题和建议，按优先级排列：
- P0：必须修复
- P1：建议修复
- P2：可选优化
5. 经验沉淀
问题修复后，回顾本次发现的问题，判断是否有可泛化的规律性教训应写入 .claude/rules/：
- 对照
architecture.md、rust-patterns.md、react-patterns.md、security.md等现有规则 - 如果某类问题反复出现但 rules 中未覆盖 → 新增规则条目
- 如果某条现有规则表述不够具体导致遗漏 → 补充细化
- 输出一张"现有 rules 覆盖 vs 缺失"对照表，标注需要新增/强化的条目
- 确认后更新对应 rules 文件
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/full-stack-code-review-mrx3xxva/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/full-stack-code-review-mrx3xxva' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/full-stack-code-review-mrx3xxva/download' --output '.skill-downloads/full-stack-code-review-mrx3xxva/SKILL.md.part' && mv '.skill-downloads/full-stack-code-review-mrx3xxva/SKILL.md.part' '.skill-downloads/full-stack-code-review-mrx3xxva/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash(git:*, cargo:*, npm:*, npx:*), Read, Glob, Grep
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/full-stack-code-review-mrx3xxva/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.