Spec Driven Development

Structures feature work for AI coding agents into gated phases — research, spec, plan, tasks, implement, validate — each producing a short reviewable artifact that constrains the next. Use when requirements are informal or drift-prone, when the same prompt produces different implementations across sessions, or when a feature touches auth, database schema, or API contracts. Keywords: spec-driven development, SDD, spec.md, plan.md, tasks.md, constitution.md, acceptance criteria, drift detection.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mariano-aguero/spec-driven-development-skill --skill spec-driven-development
Manual install
git clone --depth 1 https://github.com/mariano-aguero/spec-driven-development-skill.git /tmp/spec-driven-development-skill
mkdir -p ~/.claude/skills
cp -r /tmp/spec-driven-development-skill/. ~/.claude/skills/spec-driven-development

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Spec-Driven Development

## Overview

SDD makes **specifications the source of truth** — code serves specs, not the other way
around. Instead of prompting an AI with vague descriptions and hoping for the right output,
you define precise specifications first, then let AI generate code strictly constrained by
them.

Without a spec, AI makes thousands of micro-decisions silently. With a spec, those decisions
are made by you — explicitly, before any code is written, which is what turns a pivot into a
systematic regeneration rather than a manual rewrite.

## Quick Start

1. `/sdd:init` — create `constitution.md` (once per project, before any feature spec)
2. `/sdd:research [description]` — map how the existing code works, cited `file:line` (skip on greenfield)
3. Surface and correct the AI's implicit assumptions *before* any AC is written
4. `/sdd:specify [description]` — generate `spec.md` with MoSCoW-prioritized ACs
5. Follow the gates: Clarify → Plan → Tasks → Implement → Validate, with human approval at each

Step-by-step detail: `references/workflow-phases.md`.

## When to Use

Symptoms that signal SDD is needed:

- AI ignores constraints or generates code that doesn't match requirements
- Same prompt produces different implementations across sessions
- Requirements are complex with multiple stakeholders or cross-cutting concerns
- Team needs shared technical understanding before writing code
- Feature touches auth, data model, API contracts, or database schema
Read the full skill on GitHub

Details

Skill name
spec-driven-development
License
MIT
Repo updated
6 August 2026

FAQ

What does the Spec Driven Development skill do?

Structures feature work for AI coding agents into gated phases — research, spec, plan, tasks, implement, validate — each producing a short reviewable artifact that constrains the next. Use when requirements are informal or drift-prone, when the same prompt produces different implementations across sessions, or when a feature touches auth, database schema, or API contracts. Keywords: spec-driven development, SDD, spec.md, plan.md, tasks.md, constitution.md, acceptance criteria, drift detection.

How do I install the Spec Driven Development skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mariano-aguero/spec-driven-development-skill --skill spec-driven-development. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Spec Driven Development popular?

It lives in mariano-aguero/spec-driven-development-skill, which has 9 GitHub stars and 0 forks.

Related skills

Swe CLI Skills

8

SylphAI-Inc/swe-cli-skills

Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms

Software Development

Semi Formal Reasoning

9

knot0-com/semi-formal-reasoning

Use for code verification, debugging, and deep code analysis without running tests. This skill should be used when the user asks to "verify my changes", "check my patch", "find the bug", "why does this test fail", "are these changes correct", "review this diff", or when analyzing code semantics that require tracing execution paths. It applies semi-formal structured reasoning from the Agentic Code Reasoning paper (Ugare & Chandra, Meta, 2026) to prevent unsupported claims and force evidence-based analysis.

Software Development

Wechat Miniprogram Skill

9

Gourdbaby/wechat-miniprogram-skill

Expert guidelines for Native WeChat Mini Program development focusing on performance, code size, and native compatibility. Use when developing WeChat Mini Programs in native JavaScript.

Software Development

Openclaw Genpark Vocalist

9

alphaparkinc/openclaw-genpark-vocalist

OpenClaw GenPark Vocalist - Pure standard library acoustic time-domain autocorrelation pitch tracker and vocal stability estimator.

Software Development

Zemax Python Connect

9

Hao-xl/zemax-python-connect

当用户提到 Zemax OpticStudio Python 连接、ZOS-API 配置、独立应用程序、交互扩展、CreateNewApplication、ConnectAsExtension、ZOSAPI_NetHelper.dll、NotAuthorized、PrimarySystem None、Instance Number,或在连接 Python 与 Zemax 时遇到 --replace-current 时使用。

Software Development

Java Development

8

zander-zyx/java-development-skill

Use when writing, refactoring, or reviewing any Java or JVM code: plain Java, libraries, CLI tools, Android Java, Maven/Gradle dependency and build governance (pom.xml, BOMs, version catalogs, toolchains), Spring Boot development and version migration (2.x to 3.x, 3.x to 4.x, javax to jakarta), MyBatis/MyBatis-Plus or JPA/Hibernate persistence, writing tests with JUnit 5, Mockito, AssertJ, and Testcontainers, API design, exception handling, security review, Java upgrades, and JVM troubleshooting such as OOM, high CPU, GC tuning, GC logs, thread dumps, deadlocks, and memory leaks. Also covers J

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.