Use when designing, reviewing, or implementing HTTP APIs — error and warning handling, resource state and lifecycle, read-endpoint structure, pagination, and authentication. Triggers on error responses and formats, response envelopes, webhook payloads, how an endpoint should fail; modelling a resource lifecycle (status fields, state machines, webhook event names, enum vs parseable string); structuring read endpoints (screen-shaped/BFF vs canonical resource, aggregation, cursor vs offset pagination); and auth design (security schemes, API keys vs bearer tokens, stepped-up tokens). Apply whenever an API surfaces a failure, state change, view of data, or auth requirement to a client.
96
90%
Does it follow best practices?
Impact
99%
1.70xAverage score across 8 eval scenarios
Passed
No known issues
{
"context": "The user shares an ad-hoc auth error body and asks for a review plus a more consistent, developer-friendly shape. The criteria check whether the response critiques the specific weaknesses of the current shape and recommends the skill's unified issues conventions with a concrete before/after.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Critiques opaque numeric code",
"description": "Identifies that the numeric/opaque `code: 401` and terse `msg` are not developer-friendly or machine-actionable",
"max_score": 6
},
{
"name": "Critiques missing debug metadata",
"description": "Notes the absence of a correlationId / debuggability and that there is no path forward for the consumer",
"max_score": 4
},
{
"name": "Critiques ad-hoc inconsistent shape",
"description": "Calls out that the shape is ad-hoc and will not generalise consistently across endpoints",
"max_score": 6
},
{
"name": "Recommends unified issues array",
"description": "Recommends a unified `issues` array as the consistent shape across all endpoints",
"max_score": 8
},
{
"name": "Namespaced code, no separate type",
"description": "Recommends a single descriptive namespaced string code ({domain}.{class}.{reason}) with NO separate `type` field",
"max_score": 8
},
{
"name": "Includes severity",
"description": "The recommended shape includes a `severity` field",
"max_score": 4
},
{
"name": "Includes correlationId",
"description": "The recommended shape includes a `correlationId`",
"max_score": 6
},
{
"name": "Message title and detail",
"description": "The recommended shape carries a human-readable message (title and/or detail)",
"max_score": 4
},
{
"name": "Concrete before/after",
"description": "Shows a concrete before/after example, not just prose recommendations",
"max_score": 8
}
]
}