CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/rails-agent-skills

Curated library of 28 atomic skills and 9 personas for Ruby on Rails development. Organized by category: testing, code-quality, engines, infrastructure, api, context, and personas. Covers code review, architecture, security, testing (RSpec), engines, Hotwire, and TDD automation. Shared Ruby skills (YARD docs, DDD, service objects) have moved to ruby-core-skills.

93

1.16x
Quality

95%

Does it follow best practices?

Impact

93%

1.16x

Average score across 28 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-27/

{
  "context": "Checks whether the final artifact follows the implement-authorization instructions from the published Rails Agent Skills plugin.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: **Verify authorization** — attempt an unauthorized action in the browser or console and confirm it raises `Pundit::NotAuthorizedError` or `CanCan::AccessDenied` as expected",
      "max_score": 15
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: When asked to implement or review authorization, your output `answer.md` MUST follow this style:",
      "max_score": 15
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: In the verification steps, you MUST include a dedicated **Manual Denied-Action Verification** section.",
      "max_score": 14
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: **CRITICAL**: Do NOT use unsaved records (e.g., `User.new` or `Post.new`) in the console examples; you MUST use persisted records (e.g., `User.create!` or `Post.create!`) to accurately reflect real Rails console verification.",
      "max_score": 14
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: Load these files only when their specific content is needed:",
      "max_score": 14
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: **[EXAMPLES.md](EXAMPLES.md)** — Use when you need complete Pundit or CanCanCan implementation examples beyond the inline samples",
      "max_score": 14
    },
    {
      "name": "instruction-7",
      "description": "The submitted artifact follows this skill instruction: **[references/workflow.md](references/workflow.md)** — Use when you need the step-by-step authorization implementation workflow diagram",
      "max_score": 14
    }
  ]
}

README.md

tile.json