@laobaishare: GitHub steps in directly — from now on, no AI will write code blindly anymore. --- The newly released Spec Kit has soared to 95K stars in just a few days. The core idea is simple: make AI clearly specify what to do before touching any code. No more throwing a vague prompt and praying the agent doesn't blow up your project.
Summary
GitHub has released Spec Kit, a tool that forces AI to generate structured specifications before writing code, including understanding requirements, asking for missing details, organizing the project, and more. It significantly reduces AI-generated error-prone code and is compatible with 25+ AI agents.
View Cached Full Text
Cached at: 05/22/26, 09:58 PM
GitHub steps in,
from now on, no AI will ever write code blindly again.
Just released Spec Kit hit 95K stars in days.
Core idea in one sentence:
Make AI write down exactly what it’s going to do before touching any code.
No more throwing a vague prompt and praying the agent doesn’t blow up your project.
Spec Kit forces the AI to first produce a structured spec — understand the requirements, ask about what’s missing, organize the project, and only then start writing code.
This means fewer dumb bugs, less self-contradictory code, and much more predictable outcomes when collaborating with an agent.
The flow is simple:
/constitution → rules and standards
/specify → what you want to do
/clarify → open questions before starting
/plan → architecture and tech stack
/tasks → break down the work
/implement → start executing
Compatible with Claude Code, Cursor, Copilot, Codex, Gemini CLI — covering 25+ agents.
95K stars.
8K forks.
Open source.
GitHub steps in.
Similar Articles
@billtheinvestor: 95K: GitHub just pushed the development boundary of AI Agents one step forward. This newly open-sourced system forces AI to complete a full specification (Specs) before writing code. Raking in 95K Stars within days, the most direct consequence is that AI is shifting from 'blind code writing' to 'thinking before executing.'
An open-source system that forces AI to complete a full specification before writing code appeared on GitHub, garnering 95K Stars within days, pushing AI from blind code writing to thinking before executing.
@RoundtableSpace: GITHUB JUST OPEN SOURCED A SYSTEM THAT FORCES AI AGENTS TO WRITE FULL SPECS BEFORE CODING 95K STARS IN DAYS
GitHub open-sourced a system that forces AI agents to write full specifications before coding, quickly garnering 95,000 stars.
@wsl8297: Dug up a real treasure open-source project on GitHub: 12-Factor Agents. It distills the question of 'How to build AI Agent applications that feel like engineering and can go to production' into 12 core design principles, already with 11k+ stars on GitHub. These principles are not pulled out of thin air...
12-Factor Agents is an open-source project that condenses the core design principles for building production-grade AI Agent applications into 12 actionable engineering methodologies, covering key aspects like context management, tool calling, state modeling, etc., and has gained 11k+ GitHub stars.
@yaohui12138: Karpathy released a GitHub open-source project that truly amazed me. The project is called andrej-karpathy-skills, with 130k+ stars on GitHub. I'd call it the most useful AI engineering project of 2026. The problem it solves is extremely precise: making Cl…
Karpathy released an open-source project called andrej-karpathy-skills, centered around a 4KB CLAUDE.md file containing 4 behavioral guidelines (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). It significantly reduces AI coding error rates (up to 90%), improving code quality and development efficiency.
@GitHub_Daily: Using AI agents for production-grade tasks—writing code, running workflows, calling APIs—works fine initially, but as the scale grows, things easily get out of control: permissions too broad, context loss, and debugging becomes impossible. That's where agents-best-practices comes in: a complete guide to designing a runtime framework for AI agents, not limited to coding scenarios, but also applicable to operations, sales...
Introduces the agents-best-practices repository, a production-grade AI agent runtime framework design guide covering tool permission tiers, context compression, etc., supporting Codex and Claude Code installation.