ic-escalation-router — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ic-escalation-router (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Routes escalations to the right internal team with structured briefs, tracks resolution, and ensures nothing falls through the cracks. Part of the Internal Coordination pillar.
This is a routing, documentation, and tracking skill. It ensures the right people see the right information at the right time. The CSM decides what to escalate and at what severity; this skill handles the mechanics of getting it there and following through.
Determine the category, severity, and routing target:
| Category | Routes To | Typical Trigger | Response SLA |
|---|---|---|---|
| Product defect (bug) | Engineering via support platform | P1/P2 ticket not resolved within SLA | 4 hours acknowledge, 24-72 hours resolution depending on severity |
| Feature gap (blocking) | Product management | Customer blocked by missing capability, affecting retention | 48 hours acknowledge, 2 weeks decision on approach |
| Service failure | CS leadership + support leadership | SLA breach, repeated failures, relationship damage | 4 hours acknowledge, 24 hours remediation plan |
| Commercial dispute | CS leadership + finance | Billing issue, contract disagreement, pricing complaint | 48 hours acknowledge, 1 week resolution |
| Relationship at risk | CS leadership | Champion departure, competitive threat, strategic account declining | 24 hours acknowledge, CSM + manager strategy session within 48 hours |
| Executive intervention | CRO or CEO office | Strategic account, board-level relationship, existential churn risk | Same day acknowledge, executive response within 48 hours |
Invoke cc-internal-brief-writer with escalation context. Every brief follows this structure:
Headline (one line): What is happening, to which customer, and what is at stake. Example: "API latency issue affecting Acme Corp -- P1 open 12 days, EUR 85k ARR, renewal in 67 days"
Customer impact (2-3 sentences): How this affects the customer's business. Not just "they are unhappy" but "their analytics team cannot run reports, costing them an estimated 4 hours per week in manual workarounds."
Timeline (chronological):
Resolution attempts (what has been tried):
Specific ask (what you need):
Customer communication status:
Commercial context (when relevant):
Monitor the escalation lifecycle:
| Status | Definition | Trigger for Next Status |
|---|---|---|
| Routed | Brief sent to receiving team | Acknowledgement received |
| Acknowledged | Receiving team confirms receipt and assigns owner | Work begins |
| In progress | Active work on resolution | Resolution delivered or status update due |
| Stalled | No progress for 48 hours (critical) or 5 business days (standard) | Re-escalation flag to CSM + manager |
| Resolved | Receiving team confirms fix/response delivered | CSM confirms customer is satisfied |
| Closed | CSM confirms resolution is complete from the customer's perspective | Escalation archived |
Status update cadence:
Weekly summary for CS leadership:
{
"report_date": "2026-03-10",
"active_escalations": 7,
"new_this_week": 3,
"resolved_this_week": 2,
"stalled": 1,
"average_resolution_time_days": 4.2,
"escalations": [
{
"id": "ESC-2026-0342",
"account": "Acme Corp",
"category": "product_defect",
"severity": "critical",
"status": "in_progress",
"days_open": 5,
"owner": "Mike Ross (Eng Lead)",
"arr_at_risk": 85000,
"customer_sentiment": "frustrated_but_patient",
"next_update_due": "2026-03-11"
}
],
"trends": {
"most_common_category": "product_defect",
"avg_time_to_acknowledge": "3.1 hours",
"stall_rate": "14%"
}
}| Decision Point | Context Provided | What the Human Decides |
|---|---|---|
| Escalation initiation | Account context, issue details | Whether to escalate, at what severity, and how urgently. Not every issue warrants escalation |
| Severity classification | Suggested severity with rationale | Whether the suggested severity is correct. The CSM may override based on relationship context |
| Re-escalation | Stall notification with timeline and history | Whether to push harder, accept the timeline, or find an alternative path |
| Customer communication | Escalation status updates | What to tell the customer and when. Managing expectations during an escalation is pure human skill |
| Resolution confirmation | Receiving team's "resolved" status | Whether the resolution actually addresses the customer's need from their perspective |
Required:
Strongly recommended:
Downstream consumers:
references/routing-rules.md -- Complete routing table, acknowledgement SLAs, and re-escalation protocols~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.