CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/ruby-core-skills

Curated library of 16 public Ruby AI agent skills: 10 atomic skills (YARD docs, service objects, calculator pattern, API clients, DDD, bug triage, code review, skill routing), 5 process-discipline skills (TDD, refactoring, review, security, test planning), and 1 planning skill (TDD task generation). Zero agents — this is a foundational library consumed by framework-specific tiles like rails-agent-skills and hanakai-yaku.

95

1.05x
Quality

96%

Does it follow best practices?

Impact

95%

1.05x

Average score across 16 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-7/

{
  "context": "Checks whether the final artifact follows the test-planning-process instructions from the published Ruby Core Skills tile.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "instruction-1",
      "description": "The submitted artifact follows this skill instruction: The first failing test MUST be identified explicitly in the plan before writing it.",
      "max_score": 17
    },
    {
      "name": "instruction-2",
      "description": "The submitted artifact follows this skill instruction: All test data must be synthetic; never use real production values or API payloads in test plans.",
      "max_score": 17
    },
    {
      "name": "instruction-3",
      "description": "The submitted artifact follows this skill instruction: **Request / API Boundary:** Use when verifying HTTP statuses, headers, query parsing, or JSON payload structures.",
      "max_score": 17
    },
    {
      "name": "instruction-4",
      "description": "The submitted artifact follows this skill instruction: **Service / Business Boundary:** Use when validating domain invariants, complex calculations, or coordination between objects.",
      "max_score": 17
    },
    {
      "name": "instruction-5",
      "description": "The submitted artifact follows this skill instruction: **Unit Boundary:** Use when verifying low-level calculations, state changes on a single object, or formatting logic.",
      "max_score": 16
    },
    {
      "name": "instruction-6",
      "description": "The submitted artifact follows this skill instruction: Run the skeleton as-is — it should fail (Red). Proceed to `tdd-process` to make it pass.",
      "max_score": 16
    }
  ]
}

README.md

tile.json