create-saas
について
`create-saas`スキルは、ソロ開発者がSaaSのアイデア発見から実装準備の整ったタスクまで、完全でガイド付きのワークフローを提供します。Next.js(Prisma、Better-Auth使用)プロジェクトに特化し、検証済みのアイデア生成、PRD作成、技術アーキテクチャ設計、作業の細分化を支援します。2週間以内にSaaSアプリケーションを構築し収益化したい場合に、この対話型スキルをご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/create-saasこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
This workflow responds in the user's language while prompts are in English. It's designed for solo developers learning Next.js with Prisma and Better-Auth who want to build a monetizable SaaS in less than 2 weeks. </objective>
<quick_start> Start a new SaaS project (interactive discovery):
/create-saas
With custom project name:
/create-saas my-awesome-saas
Continue existing project:
/create-saas -c my-awesome-saas
What it does:
- Discovery: Ask questions to understand your background
- Brainstorm: Generate 3-6 validated SaaS ideas
- Validate: Challenge and refine your chosen idea
- PRD: Create Product Requirements Document
- Architecture: Design technical stack (Next.js + Prisma + Better-Auth)
- Tasks: Break down into actionable implementation tasks
Outputs saved to ~/.claude/output/saas/{project-id}/
</quick_start>
Flags:
-a/-A- Auto mode: skip confirmations (default: false)-s/-S- Save mode: save outputs to files (default: true)-c <project-id>- Continue mode: reload existing project and resume where you left off </parameters>
<state_variables> Core Variables (persist throughout all steps):
| Variable | Type | Description |
|---|---|---|
{project_name} | string | SaaS project name |
{project_id} | string | Kebab-case identifier for folders |
{auto_mode} | boolean | Skip confirmations |
{save_mode} | boolean | Save outputs to files |
{output_dir} | string | Path to output folder |
{user_language} | string | User's preferred language |
Accumulated State (grows across steps):
| Variable | Set In | Description |
|---|---|---|
{discovery_answers} | Step 1 | User's answers to discovery questions |
{has_previous_project} | Step 1 | Whether user built a project before |
{ideas} | Step 2 | List of 3-6 brainstormed ideas |
{selected_idea} | Step 2 | User's chosen idea |
{validated_idea} | Step 3 | Fully developed and validated idea |
{prd_content} | Step 4 | Product Requirements Document |
{architecture} | Step 5 | Technical architecture decisions |
{tasks} | Step 6 | List of implementation tasks |
</state_variables>
<entry_point>
Load steps/step-00-init.md
</entry_point>
<step_files>
| Step | File | Description |
|---|---|---|
| 0 | steps/step-00-init.md | Initialize: parse flags, create output folder |
| 1 | steps/step-01-discovery.md | Discovery: ask questions to find the right idea |
| 2 | steps/step-02-brainstorm.md | Brainstorm: generate 3-6 ideas, user chooses one |
| 3 | steps/step-03-validate.md | Validate: research, challenge, develop the idea |
| 4 | steps/step-04-prd.md | PRD: create Product Requirements Document |
| 5 | steps/step-05-architecture.md | Architecture: design technical stack |
| 6 | steps/step-06-tasks.md | Tasks: split into actionable implementation tasks |
| </step_files> |
<workflow_diagram>
┌──────────────┐ ┌───────────────┐ ┌───────────────┐
│ Step 0 │────►│ Step 1 │────►│ Step 2 │
│ Initialize │ │ Discovery │ │ Brainstorm │
└──────────────┘ └───────────────┘ └───────┬───────┘
│
┌────────────────────────┘
│ ▲
▼ │ (if not validated)
┌───────────────┴─┐
│ Step 3 │
│ Validate │
└────────┬────────┘
│ (if validated)
▼
┌───────────────┐ ┌───────────────┐
│ Step 4 │────►│ Step 5 │
│ PRD │ │ Architecture │
└───────────────┘ └───────┬───────┘
│
▼
┌───────────────┐
│ Step 6 │
│ Tasks │
└───────────────┘
</workflow_diagram>
<output_structure>
When {save_mode} = true, creates:
~/.claude/output/saas/{project_id}/
├── discovery.md # Discovery answers and insights
├── idea.md # Validated idea with all details
├── prd.md # Product Requirements Document
├── archi.md # Technical Architecture
├── marketing.md # Marketing strategy notes
└── tasks/ # Implementation tasks
├── 01-setup.md
├── 02-auth.md
├── ...
</output_structure>
<success_criteria>
- Discovery questions answered and insights captured
- 3-6 validated SaaS ideas generated
- One idea selected and validated against market
- PRD created with clear problem, solution, and user stories
- Technical architecture defined (Next.js + Prisma + Better-Auth)
- Implementation tasks broken down and prioritized
- All outputs saved to
~/.claude/output/saas/{project-id}/ - Project ready to start implementation </success_criteria>
Scripts:
scripts/setup.sh <project_id>- Creates output folder structurescripts/rename-project.sh <old> <new>- Renames project and updates all project_id references
Base Project:
- NOW.TS boilerplate - User provides path during step-07 setup </references>
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
Algorithmic Art Generation
メタThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
