CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/hanakai-yaku

Curated library of atomic AI agent skills for Hanami, dry-rb, and ROM Ruby development. Covers actions, slices, repositories, relations, changesets, providers, DI, operations, TDD, CLI, views, routing, and validation. Shared Ruby process skills have moved to ruby-core-skills. Uses Markdown + Front-matter architecture.

92

1.33x
Quality

94%

Does it follow best practices?

Impact

92%

1.33x

Average score across 35 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-7/

{
  "context": "Checks whether the final artifact follows the create-action instructions from the published hanakai-yaku tile.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: Use this skill when creating or reviewing Hanami 2.x Actions.",
      "max_score": 20
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: **Generate** the Action file. One Action per file — generate `Index`, `Show`, `Create`, `Update`, `Destroy` as separate classes:",
      "max_score": 20
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: **Define a Params block** to validate and coerce input. Invalid params should `halt 422` before any business logic runs:",
      "max_score": 20
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: class Create < MyApp::Action",
      "max_score": 20
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: **Inject dependencies** via `Deps` — never access the container directly (`Hanami.app['key']` is untestable and forbidden):",
      "max_score": 20
    }
  ]
}

README.md

tile.json