workflowadvancedClaude Code

End-to-End Development Workflows for Claude Code

This entry details advanced methods for automating the entire software development lifecycle using AI. It shows how to chain multiple specialized AI agents together to handle tasks from initial requirements gathering and technical design all the way to coding, testing, and final quality checks, turning a feature request into ready-to-commit code.

AI SETUP PROMPT

Paste into Claude Code — it will scan your project and set everything up

# Set Up Workflow: End-to-End Development Workflows for Claude Code

## What This Is
This entry details advanced methods for automating the entire software development lifecycle using AI. It shows how to chain multiple specialized AI agents together to handle tasks from initial requirements gathering and technical design all the way to coding, testing, and final quality checks, turning a feature request into ready-to-commit code.

Source: https://dev.to/_vjk/i-made-claude-code-think-before-it-codes-heres-the-prompt-bf

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)

Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?

## Source Access Note

The source URL (https://dev.to/_vjk/i-made-claude-code-think-before-it-codes-heres-the-prompt-bf) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.

## What to Implement

This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.

- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files

## Additional Context

- Clone the workflow showcase repository from `https://github.com/shinpr/claude-code-workflows` into a local directory named `claude-code-workflow-example`.
- Analyze the cloned repository's structure, focusing on the agent definitions (requirement-analyzer, prd-creator, task-executor) and the CLAUDE.md file to understand the command orchestration. Map these components to the user's current project structure.
- Propose a plan to integrate the `/implement`, `/review`, and `/task` commands into the user's `.claude/CLAUDE.md` file. Adapt the agent definitions and file paths from the example to match the user's project, creating the necessary agent skill files in their `.claude/skills/` directory.

## Reference Implementation

```
graph TB
A[👤 User Request] --> B[🔍 requirement-analyzer]
B --> |"📦 Large (6+ files)"| C[📄 prd-creator]
B --> |"📦 Medium (3-5 files)"| D[📐 technical-designer]
B --> |"📦 Small (1-2 files)"| E[⚡ Direct Implementation]
C --> D
D --> F[🧪 acceptance-test-generator]
F --> G[📋 work-planner]
G --> H[✂️ task-decomposer]
H --> I[🔨 task-executor]
E --> I
I --> J[✅ quality-fixer]
J --> K[🎉 Ready to Commit]
```

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

3,671 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Clone the workflow showcase repository from `https://github.com/shinpr/claude-code-workflows` into a local directory named `claude-code-workflow-example`.
02Analyze the cloned repository's structure, focusing on the agent definitions (requirement-analyzer, prd-creator, task-executor) and the CLAUDE.md file to understand the command orchestration. Map these components to the user's current project structure.
03Propose a plan to integrate the `/implement`, `/review`, and `/task` commands into the user's `.claude/CLAUDE.md` file. Adapt the agent definitions and file paths from the example to match the user's project, creating the necessary agent skill files in their `.claude/skills/` directory.

CODE INTELLIGENCE

bash

graph TB
A[👤 User Request] --> B[🔍 requirement-analyzer]
B --> |"📦 Large (6+ files)"| C[📄 prd-creator]
B --> |"📦 Medium (3-5 files)"| D[📐 technical-designer]
B --> |"📦 Small (1-2 files)"| E[⚡ Direct Implementation]
C --> D
D --> F[🧪 acceptance-test-generator]
F --> G[📋 work-planner]
G --> H[✂️ task-decomposer]
H --> I[🔨 task-executor]
E --> I
I --> J[✅ quality-fixer]
J --> K[🎉 Ready to Commit]

FIELD OPERATIONS

Automated Ticket-to-PR System

Build a workflow that watches a specific JIRA or Linear board column (e.g., 'Ready for Dev'). When a ticket moves there, an AI agent picks it up, uses the `/implement` command to generate the code, creates a PR, links it back to the ticket, and moves the ticket to 'In Review'.

Self-Healing Infrastructure Management

Using an infrastructure-as-code project (e.g., Terraform, Pulumi), create a workflow triggered by monitoring alerts. The workflow agent analyzes the alert, identifies the problematic resource, generates a code patch to fix it, runs a plan to verify the changes, and applies the fix after a brief confirmation window.

STRATEGIC APPLICATIONS

→Set up a scheduled GitHub Action that runs weekly. The action triggers a Claude Code agent to scan a random part of the codebase for tech debt (e.g., outdated patterns, poor performance), automatically refactor the code according to modern best practices, run existing tests to ensure no regressions, and open a PR for human review.
→A product manager defines a new UI component in a Product Requirements Document (PRD). The `/implement` workflow is triggered, which first generates a platform-agnostic design spec, then spawns parallel tasks to generate the component's implementation in React, Vue, and Swift (iOS) simultaneously, ensuring consistent functionality across platforms.