markusdowne/error-triage-ladder
Diagnoses and routes failures by analyzing error patterns, classifying severity, and applying retry logic, suppression budgets, and escalation rules. Use when handling errors, troubleshooting failures, recovering from API errors or timeouts, deciding whether to retry or escalate an issue, or managing service outages and tool dependency failures. Applies to any scenario where a check has failed, evidence of success is missing, or an unresolved error needs a structured response. Includes explicit untrusted-content/prompt-injection guardrails for third-party inputs.
98
1.16x
Quality
94%
Does it follow best practices?
Impact
100%
1.16xAverage score across 9 eval scenarios
rubric.jsonevals/scenario-1/
{
"context": "Evaluates whether the agent produced outputs aligned with the skill's reliability-check workflow.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Trigger conditions",
"description": "Defines explicit evidence-based trigger conditions for triage",
"max_score": 20
},
{
"name": "Tier taxonomy",
"description": "Defines cosmetic, operational, critical with distinct meaning",
"max_score": 20
},
{
"name": "Workflow sequence",
"description": "Includes explicit ordered workflow from detect to report",
"max_score": 20
},
{
"name": "Suppression budget",
"description": "Defines suppression window/recurrence thresholds and escalation rule",
"max_score": 20
},
{
"name": "Concrete mappings",
"description": "Includes at least two concrete signal-to-action examples",
"max_score": 20
}
]
}