CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/rails-agent-skills

Curated library of 41 public AI agent skills for Ruby on Rails development. Organized by category: planning, testing, code-quality, ddd, engines, infrastructure, api, patterns, context, and orchestration. Covers code review, architecture, security, testing (RSpec), engines, service objects, DDD patterns, and TDD automation. Repository workflows remain documented in GitHub but are intentionally excluded from the Tessl tile.

95

1.77x
Quality

93%

Does it follow best practices?

Impact

96%

1.77x

Average score across 41 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-13/

{
  "context": "Checks whether the final artifact follows the write-yard-docs 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 documenting Ruby classes and public methods with YARD.",
      "max_score": 10
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: All YARD text must be in English unless user explicitly requests otherwise.",
      "max_score": 10
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: Task lists from generate-tasks MUST include explicit YARD sub-tasks after implementation.",
      "max_score": 10
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: **Verify Completeness:** Run `yard stats --list-undoc` and `yard doc` to ensure no public surfaces are missing documentation.",
      "max_score": 10
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: Load these files only when their specific content is needed:",
      "max_score": 10
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: When writing or reviewing YARD docs, your output MUST satisfy:",
      "max_score": 10
    },
    {
      "name": "instruction-7",
      "description": "The submitted artifact follows this skill instruction: **Method Tags** — Every public method must have `@param` (or `@option`), `@return`, and `@raise` tags.",
      "max_score": 10
    },
    {
      "name": "instruction-8",
      "description": "The submitted artifact follows this skill instruction: **Discrete `@raise` Tags** — One `@raise` tag per exception class. Do not group multiple exceptions into a single tag.",
      "max_score": 10
    },
    {
      "name": "instruction-9",
      "description": "The submitted artifact follows this skill instruction: **Explicit Return Structures** — For `.call` methods or complex returns, the `@return` tag MUST specify the exact structure (e.g., `[Hash] Result with :success and :response keys`).",
      "max_score": 10
    },
    {
      "name": "instruction-10",
      "description": "The submitted artifact follows this skill instruction: **Tagged Notes Context** — Inline tagged notes (`TODO:`, `FIXME:`, `HACK:`, `NOTE:`, `OPTIMIZE:`) must carry actionable context (owner, ticket, next step). No naked tags.",
      "max_score": 10
    }
  ]
}

README.md

server.json

tile.json