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
94%
Does it follow best practices?
Impact
92%
1.33xAverage score across 35 eval scenarios
Passed
No known issues
{
"context": "Checks whether the final artifact follows the handle-errors 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 handling errors and halting requests in Hanami 2.x Actions.",
"max_score": 12
},
{
"name": "instruction-2",
"description": "The submitted artifact follows this skill instruction: **Core principle:** Fail fast and return meaningful error responses. Never swallow exceptions or leak internal details.",
"max_score": 11
},
{
"name": "instruction-3",
"description": "The submitted artifact follows this skill instruction: **Use `halt` for early returns**:",
"max_score": 11
},
{
"name": "instruction-4",
"description": "The submitted artifact follows this skill instruction: Halt immediately with a status code and response body for early returns. Do not rely on default success status codes (e.g. 200) for error conditions.",
"max_score": 11
},
{
"name": "instruction-5",
"description": "The submitted artifact follows this skill instruction: > **Common Mistake:** Match the error response format to the action format. Do not use `halt` with HTML error pages/strings in a JSON API action.",
"max_score": 11
},
{
"name": "instruction-6",
"description": "The submitted artifact follows this skill instruction: Always rescue `StandardError` (never rescue `Exception` as it catches system-level interrupts like `SIGTERM` or `NoMemoryError`). Log full backtraces internally, but return generic messages externally. Never rescue exceptions silently.",
"max_score": 11
},
{
"name": "instruction-7",
"description": "The submitted artifact follows this skill instruction: Do not manually inspect `request.params.valid?` or duplicate validation inside `#handle`. The action automatically halts with `422 Unprocessable Entity` before `#handle` runs if params validation fails.",
"max_score": 11
},
{
"name": "instruction-8",
"description": "The submitted artifact follows this skill instruction: Always write tests asserting on expected HTTP error status codes (e.g., 404, 422, 500) and verified error payload shapes.",
"max_score": 11
},
{
"name": "instruction-9",
"description": "The submitted artifact follows this skill instruction: Reviewers should check for these red flags:",
"max_score": 11
}
]
}docs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
skills
actions
build-json-api
create-action
handle-errors
validate-params
context
load-context
db
create-changeset
create-repository
define-relation
write-migration
dry-monads
handle-result-pattern
dry-rb
create-operation
create-validation-contract
providers
configure-providers
implement-di
review-security
routing
define-routes
slices
configure-slice
create-slice
extract-slice
review-slice-boundaries
test-slice