workflowadvancedClaude Code

Structured Production Workflow for Claude Code

This guide details a structured, 7-step process for using the Claude Code AI assistant to handle complex software development tasks in a professional setting. By defining clear review points and using project-specific documentation, development teams can increase productivity by up to 40% while maintaining code quality and control.

AI SETUP PROMPT

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

# Set Up Workflow: Structured Production Workflow for Claude Code

## What This Is
This guide details a structured, 7-step process for using the Claude Code AI assistant to handle complex software development tasks in a professional setting. By defining clear review points and using project-specific documentation, development teams can increase productivity by up to 40% while maintaining code quality and control.

Source: https://dev.to/dzianiskarviha/integrating-claude-code-into-production-workflows-lbn

## 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/dzianiskarviha/integrating-claude-code-into-production-workflows-lbn) 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

- Create a `CLAUDE.md` file in the project root. Populate it with the project's architecture (tech stack, key directories), coding standards, and a list of essential commands to provide consistent context.
- Create a `.claude/commands/` directory. Based on the user's common repetitive tasks, generate initial command templates like `/new-component.md`, `/code-review.md`, and `/feature-spec.md` to automate boilerplate and standard procedures.
- For the current development task, generate the workflow-specific markdown files: `<subtaskId>-implementation-plan.md` and `to-do.md`. Scan the task description and relevant source code to create an initial plan, then stop and prompt the user for mandatory review before proceeding to code generation.

## 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

3,259 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Create a `CLAUDE.md` file in the project root. Populate it with the project's architecture (tech stack, key directories), coding standards, and a list of essential commands to provide consistent context.
02Create a `.claude/commands/` directory. Based on the user's common repetitive tasks, generate initial command templates like `/new-component.md`, `/code-review.md`, and `/feature-spec.md` to automate boilerplate and standard procedures.
03For the current development task, generate the workflow-specific markdown files: `<subtaskId>-implementation-plan.md` and `to-do.md`. Scan the task description and relevant source code to create an initial plan, then stop and prompt the user for mandatory review before proceeding to code generation.

FIELD OPERATIONS

Automated Bug Squashing Agent

Create a `/squash-bug` command that takes a bug report ID, reads the report, analyzes the codebase for likely causes, proposes a fix in an `implementation-plan.md`, waits for approval, applies the fix, and then generates a test case to verify the fix and prevent regressions.

Self-Documenting Feature Generator

Develop a `/build-feature` command that takes a feature brief, generates a technical spec and an implementation plan, gets user approval, writes the code across multiple files, and then generates a final `implementation-overview.md` that can be used as the basis for user-facing documentation or a pull request description.

STRATEGIC APPLICATIONS