Name: new-rails-project
Rating: 37.6 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

new-rails-project

Create a new Rails project

Quality

36%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/new-rails-project/SKILL.md

The canonical home for this skill is new-rails-project in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

36%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill defines a clear tech stack and constraints for a new Rails project but falls short on actionability and workflow clarity. It reads more like a requirements document than an executable skill — it tells Claude what to build but provides no concrete commands, configuration snippets, or sequenced steps for the complex multi-technology integration. The verification step via Playwright is a nice touch but insufficient without intermediate checkpoints.

Suggestions

Add concrete executable steps: include the `rails new` command with specific flags, a sample Gemfile with the required gems and versions, and key configuration file snippets (e.g., database.yml, vite.config.ts, Inertia setup).

Define a clear sequenced workflow with numbered steps and intermediate validation checkpoints (e.g., 1. Generate Rails app, 2. Verify `rails server` works, 3. Add and configure Vite, 4. Verify Vite builds, etc.).

Remove explanatory descriptions of well-known technologies (e.g., 'Utility-first CSS framework', 'Bridges Rails and React for SPA-like experience') to improve conciseness.

Consider splitting detailed configuration templates (Gemfile, database.yml, vite.config.ts) into bundle reference files to support progressive disclosure for this complex multi-technology setup.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some unnecessary explanation. Phrases like 'Bridges Rails and React for SPA-like experience without API' and 'Utility-first CSS framework' explain concepts Claude already knows. The tech stack descriptions could be trimmed to just the library names and versions. However, it's not severely padded.	3 / 5
Actionability	The skill provides high-level requirements and constraints but lacks concrete executable steps. There are no actual commands (e.g., `rails new` with specific flags), no Gemfile snippets, no configuration file examples, and no step-by-step instructions for integrating Inertia.js with React/Vite. Claude is told what to set up but not how.	2 / 5
Workflow Clarity	There is no clear sequenced workflow for project creation. The skill lists requirements in categories but doesn't define the order of operations (e.g., generate Rails app first, then add gems, then configure Vite, etc.). The verification step at the end is good but there are no intermediate validation checkpoints. Setting up a complex multi-technology stack without intermediate validation steps is a significant gap.	2 / 5
Progressive Disclosure	The content is organized into logical sections with headers, which is good. It references @CLAUDE.md for general guidance. However, for a skill of this complexity (Rails + Inertia + React + Vite + Tailwind + Sidekiq + Redis), there's no separation into supporting files for detailed configuration examples, Gemfile templates, or setup scripts. Everything is inline but also incomplete, falling between poor and good structure.	3 / 5
	Total	10 / 20 Passed

Description

36%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is extremely terse, providing only a single action ('create') in a single domain ('Rails project') with no 'when' guidance or trigger terms. While it identifies a specific technology, it lacks the detail needed for Claude to reliably select this skill from a pool of many skills, and it provides no information about what the creation process involves or when to use it.

Suggestions

Add a 'Use when...' clause with trigger terms like 'rails new', 'new Rails app', 'Ruby on Rails project', 'scaffold a Rails application'.

Expand the 'what' to include specific actions such as 'Generates a new Ruby on Rails application with configured database, gems, and project structure'.

Include common synonyms and variations: 'Rails app', 'Ruby on Rails', 'Rails application', 'rails new command'.

Dimension	Reasoning	Score
Specificity	Names the domain (Rails project) and one action (create), but provides no further detail about what creating a Rails project entails—no mention of configuration options, database setup, gem installation, or project structure.	2 / 5
Completeness	Has a minimal 'what' (create a Rails project) but no 'when' clause at all. The lack of explicit trigger guidance caps this score. Per rubric guidelines, missing 'Use when...' should cap completeness at 3, and this barely qualifies as a 'what'.	2 / 5
Trigger Term Quality	Includes 'Rails project' which is a natural keyword users would say, but misses common synonyms and variations like 'Ruby on Rails', 'rails new', 'scaffold', 'Rails app', or 'Rails application'.	3 / 5
Distinctiveness Conflict Risk	Somewhat specific to Rails project creation, which narrows the domain, but could overlap with general project scaffolding skills, Ruby skills, or web framework setup skills. The lack of detail increases conflict risk.	3 / 5
	Total	10 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/new-rails-project/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.