Skip to content

Technical playbooks

Concrete recipes for getting the most out of Claude Code on serious team projects: code review, large refactors, testing, CI/CD, and standardization. Each one includes a ready-to-use prompt or command.

On this page

Large codebases

Use CLAUDE.md at the root and per module to provide context; /init to generate it; /compact in long sessions. Fine-tune more details in Configuration.

Generate initial repository context

Automated code review

Use /code-review and /security-review on the diff; in CI you can automate it with claude -p.

Review the local diff

Review from GitHub CLI

Terminal
gh pr diff 123 | claude -p "do a code review and comment on problems by severity"

Large-scale refactors and migrations

Combine Plan Mode to review before touching code with parallel subagents. Dig deeper in Pro workflows and Subagents.

Migration with prior planning

Testing and TDD

Ask for concrete tests and have Claude Code run them to close the loop with evidence.

Unit tests for a module

Working in TDD

CI/CD and headless mode

Use claude -p for scripts and --output-format json when you need to parse the output from another process.

Example in GitHub Actions

Terminal
- name: Claude review
  run: claude -p "review the PR changes and summarize risks" --output-format json > review.json
  env:
    ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

Standardize the team

Version the .claude/ folder in the repo with settings, skills, and agents so the whole team shares configuration, permissions, and workflows. Package the common setup as an internal plugin. See Skills and Plugins.

Internal skill for before the PR

Integrations

Connect MCP to your database or observability stack; use hooks to format on save. Continue with MCP Servers and Hooks.

Query data via MCP

Complete Aulafy mapSee how this lesson fits without leaving your path.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

  1. 1Understand
  2. 2Apply or build
  3. 3Operate with confidence
01

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

Continue into the technical branch when you need to maintain code, data, or infrastructure.

02

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

This branch prepares you to design and operate reliable AI systems.

03

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue