AI Parameters
Spec Kit · Spec-Driven Development

GitHub just killed vibe coding.

A free GitHub tool hit 111,000 stars in four months. It forces your AI to write a full spec before it writes a single line of code, and it plugs straight into Claude Code. I installed it, tested it, and this is the exact flow.

By Dr. Arpit · AI Parameters · July 2026

111K
in four months
30+
agents supported
Free
open source
1 cmd
to wire in
01   The problem

Vibe coding feels fast.
Then it quietly falls apart.

You describe an app, the AI sprints off and writes code with no plan. It looks great for twenty minutes, until the third feature contradicts the first, the model forgets its own decisions, and you are left debugging a black box you never actually designed.

Vibe coding · no plan
Prompt, code, hope

No shared spec, so the AI drifts, re-decides, and ships bugs. You become the QA for a plan that never existed.

Spec-driven · plan first
Spec, plan, tasks, code

The AI agrees on what and how before it builds, so every line traces back to an intent you approved.

02   What Spec Kit is

It flips the order
of how you build with AI.

Spec Kit is GitHub's open-source toolkit for spec-driven development. Instead of code being the first thing your agent produces, it becomes the last. You and the AI lock a spec, a plan, and a task list, then it implements. Code stops being a guess and starts being an execution of something you both signed off on.

Vibe coding asks the AI to improvise. Spec Kit asks it to rehearse first — write the script, agree on the plan, then perform.

03   Install it (30 seconds)

Two commands.
Then it lives in every project.

Spec Kit needs uv (Astral's Python tool runner). The first command installs the specify CLI globally. The second drops the whole workflow into the project you are in, wired for Claude Code.

Step 1 · install the CLI (once)
# installs the global `specify` command via uv
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git
Step 2 · add it to your project
# run inside your project — installs the Claude Code skills
specify init --here --integration claude

Open Claude Code in that folder and the /speckit commands are ready. Here is the loop you will run.

04   The workflow

Seven commands.
Code comes last, on purpose.

Run these in order inside Claude Code. Three are optional, but the optional ones are exactly what separate a clean build from a hopeful one.

01
/speckit.constitution
Set the non-negotiables

Establish your project's guardrails and principles, the rules every later step must respect. This is the AI's constitution.

02
/speckit.specify
Describe what and why, in plain English

You write the feature in natural language; Spec Kit turns it into a structured specification. No tech stack yet, just intent.

03
/speckit.clarifyoptional
Let it interrogate the gaps

The AI asks up to five sharp questions to kill ambiguity before planning. Skip this and the vagueness ends up in your code.

04
/speckit.plan
Now bring the tech stack

Give it your framework, database, constraints. It produces the technical implementation plan and design artifacts from the spec.

05
/speckit.tasks
Break it into an ordered task list

The plan becomes a dependency-ordered tasks.md, small reviewable units the agent will execute one by one.

06
/speckit.analyzeoptional
Cross-check before you build

A non-destructive consistency pass across spec, plan, and tasks. It catches contradictions while they are still cheap to fix.

07
/speckit.implement
Finally, it writes the code

The agent executes every task in tasks.md in order. Because the plan is locked, the output is an execution, not an improvisation.

05   Why it matters

What you get
for the extra five minutes.

No more drift

The spec is the single source of truth. The AI cannot quietly re-decide architecture halfway through.

Reviewable in units

You approve a spec and a task list, not a 2,000-line dump. Every change traces to an intent.

Agent-agnostic

The same workflow across Claude Code, Copilot, Cursor, Gemini and 30+ agents. Learn it once.

The honest catch

On a throwaway script it is overkill. On anything you will maintain, it is the difference between a system and a mess.


Your turn

Try it on your next build.
Then tell me how it went.

Copy the two commands, run the seven steps, and watch your AI plan before it codes. If it saved you a debugging spiral, that is the whole point.

Get Spec Kit ↗ Watch on AI Parameters ↗