agent coding skill risk: low

Rails 8 Project Generator with Inertia React

Instructs the model to generate a new Rails project named $1 using Rails 8, PostgreSQL, Inertia.js, React, Vite, Tailwind, Sidekiq, and Redis. It specifies detailed rules for datab…

External action: low

SKILL 1 file

SKILL.md

Download

---
name: new-rails-project
description: "Create a new Rails project"
---
Generate a new Rails project named $1 in the current directory. You may reference @CLAUDE.md for general guidance, though the guidance here takes precedence.

## When to Use
- You need to bootstrap a new Rails project with the opinionated stack defined in this skill.
- The project should start with Rails, PostgreSQL, Inertia.js, React, Vite, Tailwind, Sidekiq, and Redis already planned together.
- You want setup guidance that covers project creation, conventions, testing, and verification for a fresh Rails app.

# Tech Stack
Set up the following tech stack:
- **Rails ~8** with PostgreSQL - Server-side framework and database
- **Inertia.js ~2.3** - Bridges Rails and React for SPA-like experience without API
- **React ~19.2** - Frontend UI framework
- **Vite ~5** - JavaScript bundler with HMR
- **Tailwind CSS ~4** - Utility-first CSS framework
- **Sidekiq 8** - Background job processing with scheduled jobs via sidekiq-scheduler
- **Redis** - Sessions, caching, and job queue

# Rails guidance
- Do not use Kamal or Docker
- Do not use Rails "solid_*" components/systems
- Development should generally match production settings where possible
- Use Redis for caching

# Database
- All tables use UUID primary keys (pgcrypto extension)
- Timestamps use `timestamptz` for timezone awareness
- JSONB columns for flexible metadata storage
- Comprehensive indexing strategy for performance
- Encrypted fields for sensitive data (OAuth tokens, API keys)

# Background jobs
- Use Sidekiq 8 with Redis

# Testing
- Always use minitest
- Use `mocha` gem and VCR for external services (only in the providers layer)
- Prefer `OpenStruct` for mock instances
- Only mock what's necessary

# Code maintenace
- Run `bundle exec rubocop -a` after significant code changes
- Use `.rubocop.yml` for style configuration
- Security scanning with `bundle exec brakeman`

# Frontend
- All React components and views should be TSX

# General guidance
- Ask lots of clarifying questions when planning. The more the better. Make extensive use of AskUserQuestionTool to gather requirements and specifications. You can't ask too many questions.

# Verify
Verify the boilerplate is working by running `bin/rails server` and accessing the application at `http://localhost:3000` via playwright MCP.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

INPUTS

$1 REQUIRED

name of the new Rails project

e.g. myapp

REQUIRED CONTEXT

project name ($1)

OPTIONAL CONTEXT

@CLAUDE.md

TOOLS REQUIRED

AskUserQuestionTool
playwright_mcp

ROLES & RULES

Do not use Kamal or Docker
Do not use Rails "solid_*" components/systems
Development should generally match production settings where possible
Use Redis for caching
All tables use UUID primary keys (pgcrypto extension)
Timestamps use `timestamptz` for timezone awareness
JSONB columns for flexible metadata storage
Comprehensive indexing strategy for performance
Encrypted fields for sensitive data (OAuth tokens, API keys)
Use Sidekiq 8 with Redis
Always use minitest
Use `mocha` gem and VCR for external services (only in the providers layer)
Prefer `OpenStruct` for mock instances
Only mock what's necessary
Run `bundle exec rubocop -a` after significant code changes
Use `.rubocop.yml` for style configuration
Security scanning with `bundle exec brakeman`
All React components and views should be TSX
Ask lots of clarifying questions when planning
Use this skill only when the task clearly matches the scope described above
Do not treat the output as a substitute for environment-specific validation, testing, or expert review
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing

EXPECTED OUTPUT

Format

plain_text

Constraints

ask many clarifying questions before starting
follow all listed tech stack and Rails guidance rules
verify by running bin/rails server and using playwright

SUCCESS CRITERIA

Verify the boilerplate is working by running `bin/rails server` and accessing the application at `http://localhost:3000` via playwright MCP

CAVEATS

Dependencies

@CLAUDE.md
$1 (project name)

Missing context

Exact `rails new` command and flags to produce the required stack
Step-by-step integration order for Inertia, React, Vite, and Tailwind
Definition of success criteria beyond running the dev server

Ambiguities

'You may reference @CLAUDE.md' does not specify how the file is accessed or what it contains.
'Make extensive use of AskUserQuestionTool' references a tool whose availability and interface are undefined.
The 'Verify' section mixes project-setup instructions with agent execution steps without clear separation.

QUALITY

OVERALL: 0.74
CLARITY: 0.78
SPECIFICITY: 0.82
REUSABILITY: 0.72
COMPLETENESS: 0.68

IMPROVEMENT SUGGESTIONS

Replace '$1' with an explicit placeholder such as '{{project_name}}' and document its usage.
Add a 'Setup Steps' section that lists the precise sequence of commands and gem edits.
Remove or scope the 'Ask lots of clarifying questions' instruction so it does not conflict with the bootstrap purpose.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.