CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/rails-agent-skills

Curated library of 28 public AI agent skills for Ruby on Rails development. Organized by category: testing, code-quality, engines, infrastructure, api, and context. 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. Repository agents remain documented in GitHub but are intentionally excluded from the Tessl tile.

93

1.78x
Quality

95%

Does it follow best practices?

Impact

93%

1.78x

Average score across 28 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-17/

{
  "context": "Checks whether the final artifact follows the refactor-code instructions from the published Rails Agent Skills tile.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: Use this skill when the task is to change structure without changing intended behavior.",
      "max_score": 10
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: Identify the exact inputs and outputs of the logic being refactored. Keep public interfaces stable until callers are migrated. Prefer adapters, facades, or wrappers for transitional states.",
      "max_score": 10
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: **Write this before touching any production file.** No refactoring step begins until this test exists and passes on the current (un-refactored) code.",
      "max_score": 10
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: Run it: `bundle exec rspec spec/requests/orders_spec.rb` — it must pass on the **current** code. If it fails, stop and fix the characterization test or current behavior mismatch before refactoring.",
      "max_score": 10
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: Run verification after every refactoring step:",
      "max_score": 10
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: Run the full test suite.",
      "max_score": 10
    },
    {
      "name": "instruction-7",
      "description": "The submitted artifact follows this skill instruction: Use an **Observed output** label only for output copied from an actual run. Never label planned or desired results as \"Required output\", \"Expected output\", or \"Expected final output\".",
      "max_score": 10
    },
    {
      "name": "instruction-8",
      "description": "The submitted artifact follows this skill instruction: Do not write \"required exit condition\", \"must produce 0 failures\", or \"must still report 0 failures\" as evidence; run the command and paste the observed final line, or state that verification has not been run yet.",
      "max_score": 10
    },
    {
      "name": "instruction-9",
      "description": "The submitted artifact follows this skill instruction: Load these files only when their specific content is needed:",
      "max_score": 10
    },
    {
      "name": "instruction-10",
      "description": "The submitted artifact follows this skill instruction: When asked to refactor, your output MUST include:",
      "max_score": 10
    }
  ]
}

README.md

tile.json