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-15/

{
  "context": "Checks whether the final artifact follows the generate-tasks instructions from the published Rails Agent Skills tile.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: **Task 0.0:** Always \"Create feature branch\".",
      "max_score": 10
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: **Tasks format:** Each sub-task must be single action (2-5 mins).",
      "max_score": 10
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: **Paths:** Use exact file paths (`app/models/user.rb`).",
      "max_score": 10
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: **TDD:** Write spec -> Run fail -> Implement -> Run pass.",
      "max_score": 10
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: DO NOT skip Task 0.0 (Create feature branch) unless the user explicitly overrides.",
      "max_score": 10
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: DO NOT combine the TDD quadruplet sub-tasks into a single task. They must be broken out:",
      "max_score": 10
    },
    {
      "name": "instruction-7",
      "description": "The submitted artifact follows this skill instruction: b) Run spec (verify fails)",
      "max_score": 10
    },
    {
      "name": "instruction-8",
      "description": "The submitted artifact follows this skill instruction: d) Run spec (verify passes)",
      "max_score": 10
    },
    {
      "name": "instruction-9",
      "description": "The submitted artifact follows this skill instruction: **Draft Tasks:** Construct the sequential task list incorporating at least 3 TDD task groups (write spec, run fail, implement, run pass), followed by YARD, documentation updates, and a code review gate. Each TDD implementation sub-task line must name the exact file path (e.g., `spec/...`, `app/...`, `config/...`); documentation and review tasks should include relevant paths where applicable.",
      "max_score": 10
    },
    {
      "name": "instruction-10",
      "description": "The submitted artifact follows this skill instruction: **Save:** Save the output as `tasks-[feature-name].md` in `/tasks/`. Use the same `[feature-name]` as the PRD if one was provided.",
      "max_score": 10
    }
  ]
}

README.md

server.json

tile.json