Token导航 LogoToken导航

Agent Skill · 开发

clawd-code-reviewer(爪子代码审查员)

clawd-code-reviewer 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 OpenClaw 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

clawd-code-reviewer 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在开发类的 21,746 个 Skill 里排第 5,131。

总安装 6,897周安装 279GitHub Stars 公开资料未说明下载 2,165核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

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:clawd-code-reviewer(爪子代码审查员)
来源仓库:https://github.com/fuczy/clawd-code-reviewer
安装命令:
openclaw skills install clawd-code-reviewer
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install clawd-code-reviewer

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

clawd-code-reviewer 执行自动代码审查与安全漏洞扫描。集成 GitHub/GitLab/Bitbucket 并生成 PR 分析报告。通过 clawhub 安装,需结合原始 README 核验规则集定义。使用前应确认仓库访问权限及敏感信息过滤策略。适合保障代码质量与开发规范一致性。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install clawd-code-reviewer;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

clawd-code-reviewer 怎么安装?

在终端执行 openclaw skills install clawd-code-reviewer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

clawd-code-reviewer 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

clawd-code-reviewer 需要什么权限?

权限级别是接触敏感数据。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。

clawd-code-reviewer 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

clawd-code-reviewer 用的人多吗?

公开数据是累计安装 6,897 次,近一周安装 279 次,下载 2,165 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

clawd-code-reviewer 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
clawd-code-reviewer

爪子代码审查员 · 本页

6,897—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
code-reviewer
description
Automated code review, quality gates, and PR analysis. Integrates with GitHub, GitLab, Bitbucket. Enforce style guides, detect bugs, security vulnerabilities, performance issues. Auto-approve safe PRs, flag dangerous changes. Save developers 5+ hours/week on manual reviews.
homepage
https://clawhub.com/skills/code-reviewer
metadata
openclaw
emoji
🔍
requires
bins
["openclaw", "git", "github"]
tags
["devops", "code-quality", "security", "ci-cd", "github-actions"]

Code Reviewer Skill

Automate code review. Ship faster with confidence.

When to Use

✅ USE this skill when:

  • "Review all my pull requests automatically"
  • "Enforce our coding standards"
  • "Detect security vulnerabilities in PRs"
  • "Block performance anti-patterns"
  • "Auto-approve trivial changes"
  • "Generate review comments on PRs"
  • "Ensure no secrets or credentials committed"

When NOT to Use

❌ DON'T use this skill when:

  • Architecture-level changes (needs senior human review)
  • Complex business logic rewrites
  • Security-critical changes (requires human approval anyway)
  • Initial project setup (manual setup needed)

💪 The Developer Pain Point

Manual code review sucks:

  • Context switching: 15 min per PR → 5 hours/week
  • Missing subtle bugs: production incidents
  • Inconsistent standards: code quality varies
  • Slow feedback: developers wait hours/days
  • Review fatigue: important issues get missed

Our solution: Instant, consistent, comprehensive reviews Time saved: 5-10 hours/week per developer Value: $300-600/week at $60/hr → $12,000-24,000/month per dev team

Pricing: $29-99/month per repo ROI: Hours saved in first week


Features

1. Style & Linting Enforcement

rules:
  - style:
      tools: ["eslint", "prettier", "rubocop", "black", "gofmt"]
      auto_fix: true
      comment: |
        Style issues found. Run `pnpm run lint:fix` to auto-fix.

  - complexity:
      max_cyclomatic: 10
      max_nesting: 4
      comment: |
        Function too complex (cyclomatic: {{complexity}}/10). Consider refactoring.

  - duplication:
      max_lines_duplicate: 10
      ignore_tests: true

2. Bug Detection

bugs:
  - null_pointer:
      languages: ["java", "csharp", "kotlin"]
      severity: "high"

  - resource_leak:
      languages: ["go", "rust", "c++"]
      severity: "critical"

  - race_condition:
      languages: ["go", "java", "javascript"]
      patterns: ["mutex", "atomic", "promise"]

  - off_by_one:
      languages: ["c", "cpp", "java"]
      patterns: ["loop_index", "array_access"]

  - improper_error_handling:
      languages: ["python", "javascript", "ruby"]
      patterns: ["try-catch", "throw", "except"]

3. Security Scanning

security:
  - secrets_detection:
      patterns:
        - aws_secret_key: "AKIA[0-9A-Z]{16}"
        - slack_token: "xox[baprs]-[0-9a-zA-Z-]+"
        - github_token: "ghp_[0-9a-zA-Z]{36}"
        - private_key: "-----BEGIN [A-Z ]+ PRIVATE KEY-----"
      action: "fail_ci"  # Block merge
      comment: |
        🚨 **SECRET DETECTED**
        Never commit credentials! Use environment variables or secret manager.
        This PR cannot be merged until removed.

  - sql_injection:
      patterns: ["exec(.*SQL)", "raw_query(.*)", "format(.*SELECT)"]
      languages: ["python", "php", "javascript"]
      severity: "critical"

  - xss:
      patterns: ["innerHTML", "document.write", "dangerouslySetInnerHTML"]
      languages: ["javascript", "typescript", "react"]
      severity: "high"

  - path_traversal:
      patterns: ["__dirname+", "os.path.join(user_input)"]
      languages: ["node", "python"]
      severity: "high"

  - license_compliance:
      check: ["commercial_use", "copyleft", "patent_risk"]
      block_merge: true

4. Performance Anti-Patterns

performance:
  - n+1_queries:
      languages: ["ruby", "javascript", "python"]
      frameworks: ["rails", "django", "express"]
      comment: |
        N+1 query detected! Use eager loading (`.includes()` or `select_related`).

  - inefficient_loop:
      patterns: ["for(i=0;i<list.length;i++)", "for key in dict:"]
      suggest: "List comprehension / map / filter"

  - large_object_alloc:
      pattern: "new.*inside.*loop"
      comment: "Allocating object in loop → move outside"

  - blocking_io:
      pattern: "await fetch|sync_http_call"
      suggest: "Use async / non-blocking"

5. Architecture & Design

architecture:
  - god_object:
      max_methods: 20
      max_lines: 500
      comment: |
        This class is too large ({{methods}} methods, {{lines}} LOC).
        Consider splitting responsibilities.

  - feature_envy:
      pattern: "class A using data from class B extensively"
      suggest: "Move method to class B"

  - circular_dependency:
      modules: ["a", "b", "c"]
      severity: "high"

Quick Start

1. Connect Repository

# Install reviewer on a GitHub repo
clawhub code-reviewer install --repo github.com/yourorg/yourrepo

# Configure (opens editor)
clawhub code-reviewer config --repo github.com/yourorg/yourrepo

2. Enable Rules

# ~/.openclaw/code-reviewer/rules.yaml
include:
  - "security-high"
  - "style"
  - "performance"

exclude:
  - "performance/n_plus_one"  # Some false positives
    when: "test_files_only"

severity_overrides:
  - "sql_injection": "block"  # Fail CI
  - "style/variable_name": "comment"  # Just warn

3. Configure Actions

actions:
  on_pr_open:
    - "review"  # Post review comments
    - "label"  # Add labels (needs-work / safe / security)

  on_pr_update:
    - "review"  # Re-review

  auto_approve:
    when:
      - "all_checks_pass == true"
      - "author in [maintainer_team]"
      - "changed_files < 5"
    # Skip required reviewers

  block_merge:
    when:
      - "security_issues_found"
      - "test_coverage < 80%"
    message: |
      ❌ Merge blocked:
      - {{security_issues_found}} security issues
      - Test coverage {{test_coverage}}% < 80%
      Fix before merging.

GitHub App Setup

# Create GitHub App (one time)
clawhub code-reviewer create-app \
  --name "Code Reviewer" \
  --webhook-url "https://api.clawhub.com/webhooks/github" \
  --permissions "contents=read, pull_requests=write"

# Install on repositories
clawhub code-reviewer install \
  --app-id 12345 \
  --repo github.com/yourorg/yourrepo

# Or install on all org repos
clawhub code-reviewer install-org \
  --org yourorg \
  --app-id 12345

Review Comments Example

What reviewers see in PR:

🔍 **Code Review Summary**

✅ **Passed**: 12 checks
⚠️  **Warnings**: 3
❌  **Failed**: 1 (blocking)

---

### Security 🛡️

- ❌ **Hardcoded secret** in line 42 (`config.py`)
  > Remove immediately and rotate credential.

### Performance ⚡

- ⚠️  **N+1 query** in `user_controller.rb:28`
  > Use `.includes(:profile)` to load associated records in one query.

### Style 🎨

- ⚠️  **Variable name** `x` is too short (line 15)
  > Use descriptive names; min length 3 chars.

- ⚠️  **Missing trailing comma** in multi-line array (line 78)

---

💡 **Suggestions**

1. Run `./gradlew test` → 3 tests failing
2. Code coverage: 75% (target: 80%)
3. Consider adding unit tests for `PaymentProcessor` class

---

🔒 **Auto-approval status**: ❌ Not eligible (security issue blocks)

Custom Rules

Write Your Own (YAML)

custom_rules:
  - id: "no_todo_comments"
    pattern: "TODO|FIXME|HACK"
    message: "Remove technical debt comment before merging"
    severity: "warning"

  - id: "no_debugger"
    pattern: "debugger|pdb.set_trace|console.log"
    message: "Remove debugging code"
    severity: "fail"

  - id: "no_console_in_prod"
    pattern: "console.log"
    files: "src/**/*.js"
    except: "tests/**"
    severity: "warning"

  - id: "feature_flag_required"
    pattern: "if.*new_feature"
    message: "Wrap in feature flag: `if (flags.newFeature)`"
    severity: "warning"

  - id: "require_tests"
    condition: "added_lines > 50 && test_files_modified == 0"
    message: "Large change without tests. Add tests for new code."
    severity: "fail"

Python Rule Example

# rules/python/no_assert_in_prod.py
from codereviewer import Rule

class NoAssertInProd(Rule):
    def check(self, file, line):
        if line.contains("assert ") and not file.path.contains("test"):
            return self.fail("Remove assert in production code")

GitHub Actions Integration

.github/workflows/code-review.yml:

name: Code Review

on:
  pull_request:
    branches: [main, develop]

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - name: Run Code Reviewer
        uses: clawhub/code-reviewer@v1
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          config: .codereview.yaml

GitLab CI/CD

.gitlab-ci.yml:

code-review:
  stage: test
  script:
    - clawhub code-reviewer run --config .codereview.yaml
  artifacts:
    reports:
      code-review: review-report.json

Slack Notifications

notifications:
  slack:
    channel: "#code-reviews"
    on:
      - "security_issue"
      - "pr_blocked"
      - "pr_approved"
    format:
      blocks:
        - type: "header"
          text: "{{pr_title}}"
        - type: "section"
          text: "{{review_summary}}"
        - type: "actions"
          elements:
            - type: "button"
              text: "View PR"
              url: "{{pr_url}}"

Pricing

Open Source (Free)

  • Public repos: free
  • Community rules only
  • Basic style checks

Pro ($29/mo per repo)

  • Private repos
  • Custom rules
  • Security scanning
  • Slack/Teams alerts
  • Unlimited reviewers

Business ($99/mo per org)

  • All Pro features
  • Enterprise security rules
  • SSO / SAML
  • Audit logs
  • Priority support

Enterprise ($499+/mo)

  • Unlimited everything
  • Custom rule writing service
  • On-premise deployment
  • SLA guarantees
  • Dedicated engineer

Competitive Comparison

FeatureReviewDogSonarQubeCodeClimateCode Reviewer
PriceFree (self-host)$150/mo$49/mo$29/mo
GitHub integration✅✅✅✅
Custom rules✅✅⚠️ limited✅ unlimited
Auto-approve❌❌❌✅
AI suggestions❌❌❌✅
Setup timehoursdayshoursminutes

Launch Plan

  1. [x] Build core review engine
  2. [ ] Publish 50+ built-in rules
  3. [ ] Create rule marketplace (community contributed)
  4. [ ] Add AI-powered suggestions (GPT-4)
  5. [ ] Support Bitbucket, Azure DevOps
  6. [ ] Publish to GitHub Marketplace
  7. [ ] Partner with OpenClaw for integration

_Automate code reviews. Ship faster, sleep better._ 🔍✨

平台分布

OpenClaw

88.22%
按下载量换算1,910

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills