🚀 New AI-powered spec-driven development tool from GitHub

A while ago, I was talking about AI Agentic spec-driven development in one of my LinkedIn posts.

GitHub has been working on an open-source tool for just that.

👉 https://github.com/github/spec-kit

With spec-kit the workflow looks like this (copy-paste from their docs):

# Step 1: Create the feature specification

/specify Real-time chat system with message history and user presence

# This automatically:

# - Creates branch "003-chat-system"

# - Generates specs/003-chat-system/spec.md

# - Populates it with structured requirements

# Step 2: Generate implementation plan

/plan WebSocket for real-time messaging, PostgreSQL for history, Redis for presence

# Step 3: Generate executable tasks

/tasks

# This automatically creates:

# - specs/003-chat-system/plan.md

# - specs/003-chat-system/research.md (WebSocket library comparisons)

# - specs/003-chat-system/data-model.md (Message and User schemas)

# - specs/003-chat-system/contracts/ (WebSocket events, REST endpoints)

# - specs/003-chat-system/quickstart.md (Key validation scenarios)

# - specs/003-chat-system/tasks.md (Task list derived from the plan)

# Step 4: Implementation

implement specs/003-chat-system/plan.md

After implementation is complete, check if there are any build or runtime errors and fix them by copy-pasting into the prompt again.

TL;DR:

GitHub spec-kit allows you to more easily do spec driven development with different AI agents (Claude, Gemini, CoPilot etc).

You define the “what” and let the AI figure out the “how” in an iterative and controlled way.

No more manually messing around with AI agent spec readme files and more automated way of doing spec-driven AI development!