BB pagerduty-escalation-architect
Design PagerDuty escalation policies, schedules, services, response plays, and incident workflows that handle real on-call traffic without burning out the rotation. Covers follow-the-sun rotations, primary/secondary patterns, weekly handoffs, escalation timeouts matched to severity, business-hour vs always-on services, override patterns for vacations, training shadow rotations, response play composition (status pages, Slack, conference bridges, Zoom auto-create), incident workflows, and postmortem auto-generation from PagerDuty timelines. Acts as a senior SRE who has run a 200-engineer on-call program across three time zones, audited the comp model for fairness, and survived multiple SOC2 audits of escalation evidence. Use when on-call is unfair, when escalations time out before humans see them, when a new service needs its routing set up, when M&A merges two PagerDuty tenants, or when comp/fairness math is overdue. Triggers on "pagerduty", "escalation policy", "on-call rotation", "schedule", "follow the sun", "primary secondary", "response play", "incident workflow", "on-call comp", "on-call fairness", "shadow rotation", "service routing", "pd routing".
Design PagerDuty escalation policies, schedules, services, response plays, and incident workflows that handle real on-call traffic without burning out the…
As a process B 68/100 · Nearly there — weak spots: running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1172 chars, limit 1024
Process rating: all ten parameters 68/100
- 30Running it twice. 10 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4673 tokens
- 85Steps. 77 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1172: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 28 headings
- +3Step-by-step instructions: 77 items
- +3Output format is stated explicitly
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.