AC incident-triage
Structured incident triage for alerts from any monitoring source. Five-step framework: classify severity, scope blast radius, correlate with recent changes, investigate by alert type, and act (summarize, create ticket, escalate). Parses alerts from PagerDuty, Datadog, CloudWatch, Sentry, uptime monitors, GitHub Actions, AWS SNS/EventBridge, and custom webhooks. Customizable escalation policy and runbook. Uses `gh` CLI for deploy correlation. Use when: an alert fires, something is down, error rates spike, a deployment fails, investigating an incident, triaging a monitoring alert, responding to a page, or an exception tracker reports a new or regressed error.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 708 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 665: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 15 items
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.