sdd

Transform task specifications into verified code with multi-agent orchestration.

1|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/kennyolofsson23-netizen/claude-code-config --skill sdd-kennyolofsson23-netizen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sdd
Source: https://github.com/kennyolofsson23-netizen/claude-code-config/tree/main/skills/sdd
Command: npx skills add https://github.com/kennyolofsson23-netizen/claude-code-config --skill sdd-kennyolofsson23-netizen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the end-to-end transformation of informal or draft task specifications into verified, production-ready implementations, reducing manual oversight and reproducibility issues in complex development work.

Core Features & Use Cases

  • Spec-driven pipeline: Create, refine, parallelize, and implement tasks from draft to done using /sdd:add-task, /sdd:plan, and /sdd:implement.
  • Multi-agent orchestration: Specialized agents perform research, codebase analysis, architecture synthesis, decomposition, implementation, and verification.
  • LLM-as-Judge quality gates: Built-in verification rubrics, iterative fix→verify loops, and configurable thresholds to ensure artifacts meet quality criteria.
  • Use Case: Convert a feature prompt into a detailed spec, parallelize work across agents, run verified implementation, and produce a PR-ready change set.

Quick Start

Run the /sdd:implement command on a drafted .specs task file to produce and verify a working implementation.

Frequently Asked Questions about sdd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn task specifications into verified production code automatically?

Spec-driven development automates the transformation of draft task specifications into verified, production-ready code using multi-agent orchestration for research, architecture synthesis, and implementation.

What is the best way to orchestrate multiple agents for complex software implementation?

Multi-agent LLM orchestration coordinates specialized agents to perform codebase analysis, architecture synthesis, decomposition, and implementation, converting feature prompts into PR-ready change sets.

How does LLM-as-Judge verification work for automated code generation?

LLM-as-Judge verification applies built-in rubrics and configurable quality thresholds to evaluate generated artifacts, running iterative fix-and-verify loops until code meets quality criteria.

Can I use spec-driven development for complex tasks requiring codebase impact analysis?

Spec-driven development suits complex software tasks requiring research, codebase impact analysis, architecture synthesis, and decomposition, providing automated implementation workflows with artifact tracking.

Do I need a pre-drafted task file to start the spec-driven implementation pipeline?

You need a drafted .specs task file to run the implementation pipeline, which the system processes through refine-and-implement commands to produce and verify a working implementation.

What distinguishes spec-driven development from traditional TDD workflows?

Spec-driven development extends beyond traditional TDD by automating end-to-end transformation from informal specifications to verified code, reducing manual oversight and reproducibility issues through multi-agent orchestration and LLM-as-Judge quality gates.