ByteZone
Back to listClaim this project

githubDeveloper tools

Spec Kit

spec-kit

An open-source CLI toolkit for Spec-Driven Development that guides AI coding agents through structured specification, planning, and code generation steps.

  • Frontend
  • Backend
  • Full stack
  • DevOps
  • QA / Testing
  • AI coding
  • Productivity
  • Code quality
  • CLI
  • Windows
  • macOS
  • Linux
  • Self-hostable
  • Runs locally
Open websiteView on GitHub
spec-kit screenshot
Popularity
139.8k Stars
GitHub stars
Recent activity
10/1/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Addresses the lack of context, uncontrolled code generation, and inconsistent standards in AI-assisted coding through a spec-driven development workflow.

Practical value

Provides a dedicated CLI and agent slash commands to systematically execute the workflow from constitution and specification to planning and task breakdown.

Innovation / differentiation

Transforms traditional software engineering specifications into executable structured inputs for AI coding agents, shifting human-agent interaction patterns.

Leverage potential

Integrates with over 30 AI coding agents and IDE assistants, supporting custom configurations via extensions and presets.

Why now

Aligns with the rapid adoption of AI coding tools where developers urgently need to transition from prompt engineering to structured engineering management.

Community activity

In the last 90 days there were 412 new issues and 1010 pull requests; the bounded issue/PR samples include 46 issue authors and 20 PR contributors, with at least 47 releases.

Maintainer responsiveness

The 100-issue window sample had a 96% close rate, and the 99-pull-request sample had a 85% merge rate. Maintainer-response observations covered 31% of that issue sample, with a 19% response rate and median first response of 2 days.

20 contributors in PR sampleAt least 47 releasesIssue response rate 19% · sample 31 (31% coverage)Median first response 2dPR merge rate 85% · 99 sampled in window

Key highlights

  • Multi-phase SDD commands: Generates slash commands or skill files like /speckit.constitution, /speckit.specify, and /speckit.plan.
  • Extension and preset system: Supports customizing templates and commands via local overrides, presets, and extensions.
  • Multi-agent integration: Compatible with 30+ AI coding agents including GitHub Copilot CLI and Claude.

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

Runs locally

Difficulty

Easy — follow the steps

Self-hostableRuns locally
  1. 01Install specify-cli using uv: uv tool install specify-cli
  2. 02Initialize a project with the desired AI agent integration: specify init my-project --integration copilot
  3. 03Run /speckit.constitution in your AI agent to produce governing principles
  4. 04Run /speckit.specify to define what you want to build and functional requirements
  5. 05Run /speckit.plan to detail your technical stack and architecture plan
  6. 06Run /speckit.tasks to decompose the plan into actionable tasks
  7. 07Run /speckit.implement to execute code implementation according to tasks

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine

More about it

Spec Kit is an open-source Spec-Driven Development (SDD) toolkit maintained by GitHub. Instead of immediately generating code from unstructured prompts, Spec Kit organizes the workflow into discrete stages to define requirements, architecture, and tasks before execution.

Managed via the specify-cli command-line tool, Spec Kit sets up prompt files, slash commands, or agent skills directly inside project repositories. Once initialized, developers can invoke commands in their AI agent to write project guidelines (/speckit.constitution), define functional specifications (/speckit.specify), select tech stacks and architectures (/speckit.plan), and generate ordered tasks (/speckit.tasks) before executing implementation (/speckit.implement).

Beyond core code generation, the toolkit includes commands for converting tasks into GitHub Issues, running consistency checks between specs and code (/speckit.analyze), and appending remaining delta tasks (/speckit.converge). The configuration uses a tiered inheritance system consisting of project-local overrides, presets, and extensions, allowing teams to standardize development workflows across repositories.

Sources

Each field shows its status and source — expand to review.

11 · Expand

  • capability tags

    Verified

    ai_coding, productivity, code_quality

    Source: admin_cms · cms editor · 8/17/2026

  • Latest release

    Verified

    v1.0.13

    Source: GitHub API · latest_release=v1.0.13 · 10/2/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 10/2/2026

  • needs api key

    Verified

    No

    Source: admin_cms · cms editor · 8/15/2026

  • One-liner

    Verified

    {"en":"An open-source CLI toolkit for Spec-Driven Development that guides AI coding agents through structured specification, planning, and code generation steps.","zh":"一套遵循「规范驱动开发」流程的开源 CLI 工具包，配合 AI 编程 Agent 按照规范生成与执行代码。"}

    Source: admin_cms · cms editor · 8/15/2026

  • Platforms

    Verified

    windows, macos, linux

    Source: admin_cms · cms editor · 8/15/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/15/2026

  • product forms

    Verified

    cli

    Source: admin_cms · cms editor · 8/17/2026

  • role tags

    Verified

    frontend, backend, fullstack, devops, qa

    Source: admin_cms · cms editor · 8/17/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 8/15/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 8/15/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

Flare

A graph-first IDE for agentic coding featuring a live codebase map, integrated terminal, and MCP task collaboration.

Same Developer tools categoryBoth support AI coding

claude-code

An agentic coding tool for the terminal that understands codebases, handles routine development tasks, explains code, and works with Git workflows.

Same Developer tools categoryBoth support AI coding

codex

OpenAI’s coding agent that runs locally, with terminal, IDE, and desktop-app entry points.

Same Developer tools categoryBoth support AI coding

CLI-Anything

A toolkit for generating and managing agent-callable CLIs for existing software, with CLI-Hub, generation workflows, and skill/plugin integrations.

Same Developer tools categoryBoth support AI coding

openwiki

A CLI that uses agents to generate and continuously maintain Markdown wikis for codebases or personal knowledge, with a local graph visualizer.

Same Developer tools categoryBoth support Productivity

massing

Open-source, self-hosted, IFC-native AEC platform featuring in-browser BIM modeling, a general contractor portal, and development proforma tools.

Same Developer tools categoryBoth support Productivity