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-16/

{
  "context": "Checks whether the final artifact follows the apply-stack-conventions instructions from the published Rails Agent Skills tile.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: ALL new code MUST have its test written and validated BEFORE implementation.",
      "max_score": 10
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: Write the spec file content, not only the spec path: bundle exec rspec spec/[path]_spec.rb",
      "max_score": 10
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: Verify it FAILS — output must show the observed failure proving the feature does not exist yet",
      "max_score": 10
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: Write the implementation code",
      "max_score": 10
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: Verify it PASSES — run the same spec and include the observed green result line",
      "max_score": 10
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: The final artifact must show the test proof before implementation code.",
      "max_score": 10
    },
    {
      "name": "instruction-7",
      "description": "The submitted artifact follows this skill instruction: Use **Observed RED output** and **Observed GREEN output** labels for proof",
      "max_score": 10
    },
    {
      "name": "instruction-8",
      "description": "The submitted artifact follows this skill instruction: Each step should remain testable in isolation before wiring to the next layer.",
      "max_score": 10
    },
    {
      "name": "instruction-9",
      "description": "The submitted artifact follows this skill instruction: When applying stack conventions, your output MUST include:",
      "max_score": 10
    },
    {
      "name": "instruction-10",
      "description": "The submitted artifact follows this skill instruction: **Tests-first proof before implementation** — Put this section before any implementation code. For each layer, include the actual spec code written or updated, the exact command (`bundle exec rspec spec/[path]_spec.rb`), and the **Observed RED output** proving the feature is absent rather than misconfigured. Do not use placeholder or illustrative `e.g.` failure lines.",
      "max_score": 10
    }
  ]
}

README.md

tile.json