ai-coding-worflow

# Spec-driven AI Coding Workflow

This project provides a set of prompts for AI coding agents to implement a structured, two-step Plan & Execute workflow, inspired by the principles of [Kiro](https://kiro.dev/docs/specs/concepts/).

The primary motivation behind this methodology is to minimize the time and prompt iterations required to generate working code, improve overall code quality, and enable seamless switching between AI coding agents within the same project.

Inspired by [Kiro-style Prompts for Spec-Driven Development](https://github.com/andreskull/spec-driven-ai-coding), this implementation significantly simplifies documentation-driven workflow. Feature specifications are captured in a dedicated `prd.md` file, creating a shared source of truth that persists beyond individual chat sessions. This enables team collaboration and work resumption while utilizing Planner and Executor operational modes.

## The Core Workflow: Plan & Execute

The methodology is split into two distinct phases, each handled by a dedicated custom AI agent mode.

1. **Planning phase (Planner mode):** The AI acts as a senior architect. You provide a high-level feature description, and the AI guides you through an interactive process to create a complete technical specification.
1. **Execution phase (Executor mode):** The AI acts as a meticulous engineer. It reads the approved specification and implements the feature, ensuring strict adherence to the plan.

## Setting Up the Workflow

This workflow uses two distinct AI personas, each with a specific role. The setup process varies between different AI coding tools.

### Cursor (custom modes)

**1. Planner mode**

- **Name:** "☂ Planner"
- **Model:** Cursor 2.5 Pro or OpenAI GPT-5 (powerful models for complex planning)
- **Keybinding:** Cmd+Shift+1
- **Prompt:** Copy the entire content from `prompts/planner.md`
- **Context:** Enable "Full folder context"
- **Tools:** Enable "Search" section and "Edit" → "Edit & Reapply" (to generate a featu