CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-rails-project

Create a new Rails project

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%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 is a compact, well-sectioned preferences sheet that respects token budget, but it reads more like a configuration policy than an executable skill. The central scaffolding workflow (Rails + Inertia + Vite + Tailwind) lacks concrete commands and an ordered sequence, relying on Claude to figure out the fragile integration steps itself.

Suggestions

Add the concrete scaffolding commands for the core task, e.g. the exact `rails new` invocation with flags (skip-solid, database=postgresql) and the Inertia/Vite/Tailwind install steps, since the Rails+Inertia+Vite integration is the most fragile part and currently has no guidance.

Reorder the sections into an explicit numbered build sequence (scaffold -> configure database -> add job stack -> frontend -> verify) so the workflow order is unambiguous rather than implied by thematic grouping.

Trim the library glosses (e.g. "Bridges Rails and React for SPA-like experience without API", "Utility-first CSS framework") and collapse the clarifying-questions guidance to one line, since Claude already knows what these tools are.

DimensionReasoningScore

Conciseness

The body is a lean, list-based set of directives with no concept tutorials, but minor instances could be trimmed: library glosses like "Bridges Rails and React for SPA-like experience without API" and "Utility-first CSS framework" explain tools Claude already knows, and "Ask lots of clarifying questions... The more the better... You can't ask too many questions" is redundant padding.

4 / 5

Actionability

Some concrete commands are present ("bundle exec rubocop -a", "bundle exec brakeman", "bin/rails server"), but the core task — scaffolding a Rails 8 project with PostgreSQL, Inertia.js, React, Vite, and Tailwind — has no executable steps such as `rails new` flags, gem installs, or Inertia/Vite setup commands. This matches "some concrete guidance but incomplete; missing key details" rather than anchor 4, whose setup workflow would be mostly executable.

3 / 5

Workflow Clarity

The body is organized thematically (Tech Stack, Database, Testing) rather than as a sequenced workflow, leaving the build order implicit; a final validation checkpoint exists ("Verify the boilerplate is working by running `bin/rails server` and accessing the application at `http://localhost:3000` via playwright MCP"), which rules out anchor 2 ("validation absent"), but there are no intermediate checkpoints or ordered steps, so it does not reach anchor 4.

3 / 5

Progressive Disclosure

The body is under 50 lines, has no need for external reference files (none exist in the bundle), and is organized into clear, well-labeled sections (Tech Stack, Database, Background jobs, Testing, Verify), which merits a 5 under the simple-skill exception.

5 / 5

Total

15

/

20

Passed

Description

53%Weight 40%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.

The description is clear, concise, and in third person, but it is minimal: one action, no trigger guidance, and no hint of the distinctive stack (Inertia.js, React, Vite, Tailwind, Sidekiq) that differentiates this skill. Adding a "Use when..." clause and one or two stack specifics would raise most dimensions at negligible token cost.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create/scaffold a new Rails app or start a new Rails project."

Mention the distinctive stack (e.g. "with PostgreSQL, Inertia.js, React, Vite, and Tailwind") so the description both covers the skill's actual scope and distinguishes it from generic Rails skills.

Include natural synonyms such as "app" and "scaffold" alongside "project" to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Create a new Rails project" names the domain and one concrete action, matching anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive"); it does not reach anchor 4 because it lists only a single action and omits the concrete setup work the skill actually performs (PostgreSQL, Inertia.js, Sidekiq configuration).

3 / 5

Completeness

The "what" is clear (create a new Rails project) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; this is not a 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

"Rails" and "new... project" are natural terms a user would say, but the description misses common variations like "app", "application", or "Ruby on Rails", fitting anchor 3 ("Some relevant keywords but missing common variations or synonyms") rather than anchor 4's multi-term coverage.

3 / 5

Distinctiveness Conflict Risk

"Rails" carves out a clear niche with a distinct trigger, but a description this terse could overlap with general Rails-development or app-scaffolding skills, matching anchor 4 ("Mostly distinct; minor overlap risk with closely related skills") rather than anchor 5's fully distinct trigger set.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/new-rails-project/SKILL.md

Reviewed

Table of Contents

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.