Back to browse
GitHub Repository

A Claude skill that keeps your AI coding tools from contradicting each other. Generates requirements.md, design.md, and tasks.md before any code is written — then creates matching config files for Claude Code, Cursor, Copilot, Windsurf, and Aider.

90 starsPython

I Made a Claude Skill for SDD

by NTRIXLM·May 21, 2026·40 points·17 comments

AI Analysis

MidSolve My Problem

Spec-first workflow for AI agents when Cursor and Kiro already handle context.

Strengths
  • Enforces shared context via three specific markdown files before code generation.
  • Includes CI pipeline with static assertions and behavioral tests for the skill itself.
  • Addresses real drift problem when switching between different AI coding assistants.
Weaknesses
  • Requires manual skill installation and setup compared to native IDE integrations.
  • Competes with built-in context management in funded tools like Cursor and Kiro.
Category
Target Audience

Developers using multiple AI coding tools (Cursor, Claude Code, Copilot)

Similar To

Cursor · Kiro · GitHub Copilot

Post Description

At my work they provided a single Claude subscription for everyone on the team. To be honest I like kiro better as it provides a way better SDD management. But the company can't provide it and I can't afford it yet. Turns out I had the skill creator skill in my claude instance so I made use of it to create this Skill. I made it fully by using Claude but I wanted to make it open source, so I asked it to help me make tests and preparations for it, even a CI to run python tests. Well, we got this results with it: - Phase 2A: 67 static assertions (Python script, runs in CI) - Phase 2B: 15 behavioral tests (live Claude Code session) - Phase 2C: 53 generation quality checks across 3 end-to-end flows All of these passed and the CI also passed (after a few tries). I made it to suit my way of prompting and coding and based it off kiro's SDD management, but I want it to be publicly available and used by many people. According to claude some of the testers need to fit the following criteria: 1. Developer starting a real new project from scratch 2. Solo dev with an active side project (greenfield or partial codebase) 3. Team lead whose team uses multiple AI tools 4. Developer with an existing codebase and no written specs 5. Developer who actively uses 3+ AI coding tools It's actually a blind test, no guiding, just try it if you can, I'd really appreciate your help. The repo is here: https://github.com/FredAntB/Spec-Driven-Development

Similar Projects

Design Skills

Curated markdown collection when awesome lists already exist everywhere.

Niche Gem
elwingo1
301mo ago
AI/ML●●Solid

Mp4 or mov to detailed design spec MCP

Screen recordings to design specs when screenshot-to-code tools already exist.

Solve My ProblemSlick
Meliwat93
301mo ago