Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

dev-review开发审查

Agent Skill

dev-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

196

周安装

8

GitHub Stars

公开资料未说明

下载量

63
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:dev-review(开发审查)
来源仓库:https://github.com/codihaus/claude-skills
仓库路径:skills/dev-review
安装命令:
npx skills add https://github.com/codihaus/claude-skills --skill dev-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/codihaus/claude-skills --skill dev-review

简介

dev-review 提供代码审查功能,帮助检查代码质量、安全性和规范符合性,适用于 PR 提交前或功能实现后的质量把关。

  • 它聚焦变更内容的上下文分析,识别回归风险和新引入问题,输出专业且直接的反馈意见。
  • 可通过命令行指定文件或目录进行审查,支持暂存区、特定路径或工单编号等多种调用方式。
  • 使用前请确保具备相应代码访问权限,注意该技能可能读取本地文件和执行系统命令,需评估隐私与合规要求。
  • dev-review 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/dev-review - Code Review

Skill Awareness: See skills/_registry.md for all available skills. - Before: After /dev-coding implementation - If issues: Fix with /dev-coding, then review again - If major changes: Create CR via /debrief

Review code changes for quality, security, and adherence to standards.

When to Use

  • After implementing a feature
  • Before merging a PR
  • To get feedback on approach
  • To catch issues before production

Usage

/dev-review                      # Review uncommitted changes
/dev-review --staged             # Review staged changes only
/dev-review src/auth/            # Review specific directory
/dev-review UC-AUTH-001          # Review changes for specific UC

Input

Reviews can be based on:

  1. Git diff - Uncommitted or staged changes
  2. File list - Specific files to review
  3. UC reference - Files changed for a use case (from spec)

Output

## Review Summary

**Verdict**: ✅ Approve | ⚠️ Request Changes | ❓ Needs Discussion

**Stats**: X files, Y additions, Z deletions

### Issues Found

#### 🔴 Critical (must fix)
- [security] SQL injection risk in `src/api/users.ts:45`
- [bug] Null pointer in `src/utils/parse.ts:23`

#### 🟡 Important (should fix)
- [performance] N+1 query in `src/api/posts.ts:67`
- [error-handling] Unhandled promise rejection

#### 🔵 Suggestions (nice to have)
- [style] Consider extracting to helper function
- [naming] `data` is too generic, suggest `userProfile`

### By File
- `src/api/auth.ts` - 2 issues
- `src/components/Form.tsx` - 1 suggestion

### Positives
- Good error handling in login flow
- Clean separation of concerns

Workflow

Phase 1: Gather Context

1. Get changes to review
   → git diff (uncommitted)
   → git diff --staged (staged only)
   → Read specific files

2. Read project conventions
   → plans/scout/README.md (Conventions section)
   → CLAUDE.md
   → .eslintrc, tsconfig.json

3. Read related spec (if UC provided)
   → plans/features/{feature}/specs/{UC}/README.md

Phase 2: Analyze Changes

For each changed file:

1. Understand the change
   - What was added/modified/removed?
   - What is the intent?

2. Check against spec (if available)
   - Does implementation match spec?
   - Any missing requirements?

3. Run through checklists
   - Security
   - Performance
   - Error handling
   - Style/conventions
   - Testing

Phase 3: Security Review

## Security Checklist

[ ] **Input Validation**
    - User input sanitized?
    - SQL/NoSQL injection prevented?
    - XSS prevented (HTML escaped)?

[ ] **Authentication**
    - Auth required where needed?
    - Token validated correctly?
    - Session handled securely?

[ ] **Authorization**
    - Permissions checked?
    - Can't access others' data?
    - Admin functions protected?

[ ] **Data Protection**
    - Passwords hashed?
    - Sensitive data not logged?
    - No secrets in code?

[ ] **API Security**
    - Rate limiting present?
    - CORS configured?
    - No sensitive data in URLs?

Common Security Issues:

// BAD: SQL injection
const query = `SELECT * FROM users WHERE id = ${userId}`;

// GOOD: Parameterized
const query = `SELECT * FROM users WHERE id = $1`;
await db.query(query, [userId]);

// BAD: XSS vulnerable
element.innerHTML = userInput;

// GOOD: Escaped
element.textContent = userInput;

// BAD: Hardcoded secret
const apiKey = "sk-1234567890";

// GOOD: Environment variable
const apiKey = process.env.API_KEY;

Phase 4: Quality Review

## Quality Checklist

[ ] **Error Handling**
    - Errors caught and handled?
    - User-friendly error messages?
    - Errors logged for debugging?
    - No swallowed errors?

[ ] **Performance**
    - No N+1 queries?
    - Large lists paginated?
    - Heavy operations async?
    - No memory leaks?

[ ] **Maintainability**
    - Code readable?
    - Functions not too long?
    - No magic numbers/strings?
    - DRY (no unnecessary duplication)?

[ ] **Testing**
    - New code has tests?
    - Edge cases covered?
    - Tests actually test something?

Common Quality Issues:

// BAD: N+1 query
const posts = await getPosts();
for (const post of posts) {
  post.author = await getUser(post.authorId); // Query per post!
}

// GOOD: Batch query
const posts = await getPosts({ include: { author: true } });

// BAD: Swallowed error
try {
  await doSomething();
} catch (e) {
  // Nothing - error disappears!
}

// GOOD: Handle or rethrow
try {
  await doSomething();
} catch (e) {
  logger.error('Failed to do something', e);
  throw new AppError('Operation failed', e);
}

// BAD: Magic number
if (retries > 3) { ... }

// GOOD: Named constant
const MAX_RETRIES = 3;
if (retries > MAX_RETRIES) { ... }

Phase 5: Convention Review

## Convention Checklist (from scout)

[ ] **Naming**
    - Variables: {convention from scout}
    - Files: {convention from scout}
    - Components: {convention from scout}

[ ] **Structure**
    - File in correct location?
    - Follows project patterns?
    - Imports organized?

[ ] **Style**
    - Matches .prettierrc / .eslintrc?
    - Consistent with codebase?
    - No linting errors?

[ ] **Git**
    - Commit message format correct?
    - No unrelated changes?
    - No debug code / console.log?

Phase 6: Spec Compliance (if UC provided)

## Spec Compliance

### Requirements Met
- [x] Login endpoint created
- [x] Returns token on success
- [x] Returns error on invalid credentials

### Requirements Not Met
- [ ] Rate limiting not implemented (spec said 5 attempts/min)

### Not in Spec
- Added "remember me" checkbox (is this approved?)

Phase 7: Generate Review

Compile findings into review output format.

Severity Levels:

LevelIconMeaningAction
Critical🔴Security risk, bug, breaks functionalityMust fix before merge
Important🟡Performance, maintainability issuesShould fix
Suggestion🔵Style, improvementsNice to have
PositiveGood practice notedEncouragement

Review Verdicts:

VerdictWhen
✅ ApproveNo critical/important issues
⚠️ Request ChangesHas critical or multiple important issues
❓ Needs DiscussionUnclear requirements, architectural concerns

Review Best Practices

Be Constructive

// BAD
"This code is bad"

// GOOD
"This could cause a SQL injection. Consider using parameterized queries:

SELECT * FROM users WHERE id = $1

Explain Why

// BAD
"Don't use var"

// GOOD
"Use const/let instead of var - var has function scope which can lead to
unexpected behavior. const also signals intent that the value won't change."

Suggest Alternatives

// Issue + Solution
"The N+1 query here will cause performance issues with many posts.

Consider using an include/join:

const posts = await db.posts.findMany({ include: { author: true } });

Acknowledge Good Work

### Positives
- Clean separation of API and business logic
- Good error messages for users
- Comprehensive input validation

Tools Used

ToolPurpose
Bashgit diff, git log
ReadRead changed files
GrepSearch for patterns
GlobFind related files

Integration

SkillRelationship
/dev-codingReview after implementation
/dev-scoutGet project conventions
/dev-specsCheck spec compliance

Example Review

User: /dev-review UC-AUTH-001

Phase 1: Gather
- Get git diff for UC-AUTH-001 files
- Read scout conventions
- Read UC-AUTH-001 spec

Phase 2-6: Analyze
- src/api/auth/login.ts: Clean ✓
- src/components/LoginForm.tsx: 1 issue
- src/lib/api.ts: 1 suggestion

Phase 7: Output

## Review Summary

**Verdict**: ⚠️ Request Changes

**Stats**: 3 files, +245 additions, -12 deletions

### Issues Found

#### 🔴 Critical
None

#### 🟡 Important
- [error-handling] `src/components/LoginForm.tsx:34`
  Promise rejection not handled. If API fails, user sees nothing.

// Add error state .catch(err => setError(err.message))


#### 🔵 Suggestions

- [naming] `src/lib/api.ts:12` `data` is generic. Consider `credentials` for clarity.

### Spec Compliance

- POST /api/auth/login works
- Returns token
- Validates input
- Missing: Rate limiting (spec requirement)

### Positives

- Good validation on both client and server
- Clean component structure
- Proper TypeScript types

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.11%
按下载量换算23

Claude

29.77%
按下载量换算19

Cursor

20.46%
按下载量换算13

Gemini CLI

8.84%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills