For OpenClaw v2026.2 | Requires coding-agent, git-workflows, and test-runner skills, plus project codebase access.

TL;DR: Code review: Agent analyzes PR changes and generates review reports. Automated testing: "test-runner": {"frameworks": ["jest", "vitest"]}. CI/CD integration: Webhook receives GitHub/GitLab events. Multi-project management: "projects": {"frontend": {...}, "backend": {...}}. Core command: openclaw agent --message "Review this PR".

Practice Goals

Build an AI coding assistant that can:

1. Automate code review
2. Run tests and report results
3. Generate code documentation
4. Integrate with CI/CD pipelines
5. Switch context across multiple projects

Install Required Skills

# Programming-related skills
openclaw skill install coding-agent
openclaw skill install debug-pro
openclaw skill install git-workflows
openclaw skill install docker-essentials

# Testing skills
openclaw skill install test-runner

Code Review Automation

Configure Code Review

---
name: code-review-assistant
version: 1.0.0
description: Automated code review with OpenClaw
triggers:
  - code review
  - PR review
  - review
---

# Code Review Assistant

Automate code review for pull requests.

## Features

- Review code changes
- Check for common issues
- Suggest improvements
- Generate review comments

## Review Checklist

1. **Code Quality**
   - Naming conventions
   - Code structure
   - Error handling

2. **Security**
   - SQL injection
   - XSS vulnerabilities
   - Secret exposure

3. **Performance**
   - N+1 queries
   - Memory leaks
   - Inefficient algorithms

4. **Best Practices**
   - DRY principle
   - SOLID principles
   - Design patterns

Code Review Scenario

User: Review this PR

Agent: Sure, let me review PR #123...

[Fetch PR info]
[Analyze code changes]
[Check for potential issues]

## PR #123 Review Report

### Overview
- Branch: feature/user-search
- Changes: +156 -23
- Files: 8

### Issues Found

**Critical** (1):
- 🚨 `auth.js:45` - Plain-text password storage risk

**Warnings** (3):
- ⚠️ `search.js:23` - Potential SQL injection
- ⚠️ `user.js:78` - Unhandled Promise
- ⚠️ `utils.js:12` - Deprecated API

**Suggestions** (5):
- 💡 Consider adding unit tests
- 💡 Use constants instead of magic numbers
- 💡 Suggest adding error boundaries
- 💡 Consider extracting common methods
- 💡 Suggest adding type annotations

### Code Highlights
- ✅ Good function naming
- ✅ Reasonable module structure
- ✅ Appropriate comments

Would you like me to generate review comments?

Automated Testing

Test Runner Configuration

{
  "skills": {
    "test-runner": {
      "frameworks": ["jest", "vitest", "pytest"],
      "coverage": {
        "enabled": true,
        "threshold": 80
      },
      "reporting": {
        "format": "markdown",
        "output": "test-report.md"
      }
    }
  }
}

Test Scenario

User: Run tests and report results

Agent: Running tests...

[Execute test commands]
[Collect test results]
[Analyze coverage]

## Test Report

### Test Results
- Total: 45 tests
- Passed: 42 ✅
- Failed: 2 ❌
- Skipped: 1 ⏭️

### Failed Tests

**1. UserSearch.test.js**

AssertionError: expected [] to equal [{id: 1, name: ’test’}]

Suggestion: Check database connection or mock data

**2. Auth.test.js**

Timeout: Async callback not invoked within 5000ms

Suggestion: Increase timeout or check async logic

### Coverage

| File | Statements | Branches | Functions | Lines |
|-----|-----|-----|-----|-----|
| auth.js | 85% | 78% | 90% | 85% |
| search.js | 72% | 65% | 80% | 70% |
| user.js | 90% | 85% | 95% | 90% |
| **Total** | **82%** | **76%** | **88%** | **82%** |

Would you like me to fix the failed tests?

CI/CD Integration

GitHub Actions Integration

# .github/workflows/openclaw-review.yml
name: OpenClaw Review

on:
  pull_request:
    types: [opened, synchronize]

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      
      - name: Setup OpenClaw
        run: npm install -g openclaw@latest
        
      - name: Run Review
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
        run: |
          openclaw agent --message "Review PR #${{ github.event.pull_request.number }}" \
            --output review-comment.md
            
      - name: Post Comment
        uses: actions/github-script@v6
        with:
          script: |
            const fs = require('fs');
            const comment = fs.readFileSync('review-comment.md', 'utf8');
            await github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body: comment
            });

Automated Deployment

User: Deploy to staging

Agent: Deploying to staging environment...

[Pull latest code]
[Run tests]
[Build project]
[Deploy to server]

## Deployment Report

### Deployment Info
- Environment: staging
- Branch: main
- Commit: abc1234
- Time: 2026-02-26 15:30

### Deployment Steps
1. ✅ Pull code
2. ✅ Install dependencies
3. ✅ Run tests (45/45 passed)
4. ✅ Build project
5. ✅ Deploy to server

### Health Check
- API: ✅ OK
- Database: ✅ Connected
- Redis: ✅ Connected

### Access URLs
- URL: https://staging.example.com
- API: https://api-staging.example.com

Deployment successful!

Multi-Project Management

Project Configuration

{
  "projects": {
    "frontend": {
      "path": "~/projects/frontend",
      "skills": ["coding-agent", "test-runner"],
      "context": "AGENTS.md"
    },
    "backend": {
      "path": "~/projects/backend",
      "skills": ["coding-agent", "docker-essentials"],
      "context": "AGENTS.md"
    },
    "mobile": {
      "path": "~/projects/mobile",
      "skills": ["coding-agent"],
      "context": "AGENTS.md"
    }
  }
}

Project Switching

User: Switch to backend project

Agent: Switched to backend project.

Current project info:
- Name: backend
- Path: ~/projects/backend
- Stack: Python/FastAPI
- Recent commit: Add user authentication

What would you like me to help with?

Code Generation

Generate Boilerplate Code

User: Create CRUD API for User model

Agent: Sure, I'll create a CRUD API for the User model...

[Analyze existing code structure]
[Generate code files]

Generated the following files:

**1. models/user.py**
```python
from pydantic import BaseModel
from datetime import datetime

class User(BaseModel):
    id: int
    name: str
    email: str
    created_at: datetime
    updated_at: datetime

class UserCreate(BaseModel):
    name: str
    email: str

class UserUpdate(BaseModel):
    name: str | None = None
    email: str | None = None

2. routers/users.py

from fastapi import APIRouter, HTTPException
from models.user import User, UserCreate, UserUpdate

router = APIRouter(prefix="/users", tags=["users"])

@router.get("/", response_model=list[User])
async def list_users(): ...

@router.get("/{user_id}", response_model=User)
async def get_user(user_id: int): ...

@router.post("/", response_model=User)
async def create_user(user: UserCreate): ...

@router.put("/{user_id}", response_model=User)
async def update_user(user_id: int, user: UserUpdate): ...

@router.delete("/{user_id}")
async def delete_user(user_id: int): ...

3. tests/test_users.py

from fastapi.testclient import TestClient

def test_list_users(): ...
def test_create_user(): ...
def test_update_user(): ...
def test_delete_user(): ...

Would you like me to run tests to verify?

## Documentation Generation

### API Documentation

User: Generate documentation for this API

Agent: Analyzing API endpoints…

[Scan route files] [Extract API info] [Generate documentation]

API Documentation

User Module

GET /users

Get user list

Parameters

Response

{
  "data": [User],
  "total": int,
  "page": int,
  "limit": int
}

POST /users

Create user

Request Body

{
  "name": "string",
  "email": "string"
}

Response

{
  "id": 1,
  "name": "string",
  "email": "string",
  "created_at": "2026-02-26T00:00:00Z",
  "updated_at": "2026-02-26T00:00:00Z"
}

Save to docs/api.md?

## Troubleshooting

### CI/CD Issues

```bash
# Check CI/CD status
openclaw ci status

# View CI/CD logs
openclaw ci logs --last

# Retry failed jobs
openclaw ci retry

Code Issues

# Analyze code issues
openclaw analyze --project backend

# Generate fix suggestions
openclaw suggest --file auth.js

Summary

Building a coding assistant with OpenClaw:

• Code Review: Automated PR review
• Test Execution: Automated testing and reporting
• CI/CD Integration: Automated deployment workflows
• Multi-Project Management: Quick context switching
• Code Generation: Boilerplate code generation
• Documentation Generation: Automatic API documentation

Changelog:

• 2026-02-26: Initial release

Series Navigation:

• ← Previous: Practice: Building an Office Automation Assistant
• → Next: Practice: Building a Smart Home Control Center