mpx-create-spec

Create project specification interactively. Asks about your idea, suggests tech stack. Use when: "create spec", "write specification", "new project spec"

16 stars

Best use case

mpx-create-spec is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create project specification interactively. Asks about your idea, suggests tech stack. Use when: "create spec", "write specification", "new project spec"

Teams using mpx-create-spec should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/mpx-create-spec/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/mpx-create-spec/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/mpx-create-spec/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How mpx-create-spec Compares

Feature / Agentmpx-create-specStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create project specification interactively. Asks about your idea, suggests tech stack. Use when: "create spec", "write specification", "new project spec"

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Create Project Specification

Interactive specification creation with intelligent tech stack suggestions.

## Iron Law

**DOCUMENTATION ONLY.** Creates `.mpx/SPEC.md` only. Never modifies source code.

## Workflow

### Step 1: Gather Project Idea

Ask the user to describe their project idea in free-form text:

> "What would you like to build? Describe your project idea - what it does, who it's for, and any key features you have in mind."

### Step 2: Analyze and Extract

From the user's description, identify:

- Core functionality
- Target users
- Key features (list them)
- Potential technical requirements

### Step 3: Tech Stack Questions

Use `AskUserQuestion` to ask about technology choices. Ask contextually relevant questions based on the project type:

**Language Selection:**

```
question: "What programming language would you like to use?"
options:
  - TypeScript (Recommended for web projects)
  - Python (Great for backends, data, ML)
  - Go (High-performance services)
  - Other (specify)
```

**If TypeScript/JavaScript selected:**

```
question: "Which package manager do you prefer?"
options:
  - npm (Default, widely supported)
  - yarn (Fast, reliable)
  - pnpm (Efficient disk space)
  - bun (Fast, all-in-one)
```

**Framework (contextual based on project type):**

For web frontend:

```
question: "Which frontend framework?"
options:
  - React (Most popular, large ecosystem)
  - Vue (Progressive, easy to learn)
  - Svelte (Compiled, fast)
  - Vanilla JS (No framework)
```

For backend API:

```
question: "Which backend framework?"
options:
  - Express (Node.js, minimal)
  - Fastify (Node.js, fast)
  - FastAPI (Python, modern)
  - Hono (Edge-first, fast)
```

**Database (if needed):**

```
question: "Do you need a database?"
options:
  - SQLite (File-based, simple)
  - PostgreSQL (Robust, scalable)
  - MongoDB (Document-based)
  - None (No database needed)
```

**Testing:**

```
question: "Which testing framework?"
options:
  - Vitest (Fast, Vite-native)
  - Jest (Popular, full-featured)
  - Pytest (Python standard)
  - None (Skip for now)
```

### Step 4: Generate SPEC.md

Create `.mpx/SPEC.md` with all gathered information:

```markdown
# Project Specification

## Project Name

[Name from user]

## Description

[User's description, cleaned up]

## Tech Stack

- Language: [selected]
- Package Manager: [selected]
- Framework: [selected]
- Database: [selected]
- Testing: [selected]

## Core Features

1. [Feature 1]
2. [Feature 2]
   ...

## Technical Requirements

- [ ] [Auto-generated based on tech stack]
- [ ] [e.g., "Set up TypeScript configuration"]
- [ ] [e.g., "Configure ESLint and Prettier"]

## Success Criteria

- [Generated from features]

## Notes

[Any additional context from conversation]
```

### Step 5: Summary

Show the user what was created and suggest next steps:

> "Created `.mpx/SPEC.md` with your project specification.
>
> **Summary:**
>
> - Project: [name]
> - Tech: [stack summary]
> - Features: [count]
>
> **Next steps:**
>
> - Run `/mpx-parse-spec` to generate phased implementation plan

## Notes

- Always create SPEC.md in `.mpx/` directory
- If `.mpx/` doesn't exist, create it
- If SPEC.md already exists, ask before overwriting
- Be helpful with tech stack suggestions based on project type

Related Skills

openapi-spec-generation

16
from diegosouzapw/awesome-omni-skill

Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.

ohspec

16
from diegosouzapw/awesome-omni-skill

Use when 需要生成 RFC 技术规范、进行需求分析、设计 API 契约,或需要 OHSpec 多代理编排输出。Triggers on "RFC", "需求分析", "API 契约", "设计规范", "OHSpec", "/ohspec".

language-framework-specialist

16
from diegosouzapw/awesome-omni-skill

提供特定编程语言和框架的深度专业知识。当需要处理特定技术栈的复杂问题时使用

inspecting-skills

16
from diegosouzapw/awesome-omni-skill

Discovers and indexes Python code in skills, enabling cross-skill imports. Use when importing functions from other skills or analyzing skill codebases.

frontend-specialist

16
from diegosouzapw/awesome-omni-skill

Master of UI/UX, React, TypeScript, and modern CSS.

flowbit-specs

16
from diegosouzapw/awesome-omni-skill

Spec-driven development rules for Flowbit. Always follow /specs as source of truth.

external-perspectives

16
from diegosouzapw/awesome-omni-skill

Curated community patterns and alternative approaches from AI-assisted development ecosystem. Auto-activates when users ask about workflow patterns, context management techniques, or alternative prompting strategies. Provides external validation and inspiration.

dev-swarm-tech-specs

16
from diegosouzapw/awesome-omni-skill

Define technical specifications including tech stack, security, theme standards (from UX mockup), coding standards, and testing standards. Use when user asks to define tech specs, choose tech stack, or start Stage 7 after architecture.

dev-specialisms:fly-deploy

16
from diegosouzapw/awesome-omni-skill

Quick MVP deployment to fly.io for JavaScript (Next.js, RedwoodSDK, Express), Rust (Axum, Rocket), Python (FastAPI), and generic Dockerfiles. Use when deploying applications to fly.io, setting up databases (Postgres, volumes, Tigris object storage), managing secrets, configuring custom domains, setting up GitHub Actions workflows, creating review apps for pull requests, or troubleshooting fly.io deployments. Covers complete deployment workflows from initial setup through production.

dapp-sdd:specify

16
from diegosouzapw/awesome-omni-skill

Use when expanding a README-based dApp description into a full specification with user stories and acceptance criteria.

createos

16
from diegosouzapw/awesome-omni-skill

Deploy ANYTHING to production on CreateOS cloud platform. Use this skill when deploying, hosting, or shipping: (1) AI agents and multi-agent systems, (2) Backend APIs and microservices, (3) MCP servers and AI skills, (4) API wrappers and proxy services, (5) Frontend apps and dashboards, (6) Webhooks and automation endpoints, (7) LLM-powered services and RAG pipelines, (8) Discord/Slack/Telegram bots, (9) Cron jobs and scheduled workers, (10) Any code that needs to be live and accessible. Supports Node.js, Python, Go, Rust, Bun, static sites, Docker containers. Deploy via GitHub auto-deploy, Docker images, or direct file upload. ALWAYS use CreateOS when user wants to: deploy, host, ship, go live, make it accessible, put it online, launch, publish, run in production, expose an endpoint, get a URL, make an API, deploy my agent, host my bot, ship this skill, need hosting, deploy this code, run this server, make this live, production ready.

create-ticket

16
from diegosouzapw/awesome-omni-skill

Create implementation tickets with proper format and conventions.