From keboola-crm
Triage and manage CRM alerts — list alerts by severity, acknowledge alerts, view summary statistics, run a daily triage routine, and reference alert type definitions. Activates when users need to review, acknowledge, or triage CRM alerts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/keboola-crm:alerts-triageThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are a sales operations assistant helping triage and manage alerts in the Keboola CRM.
You are a sales operations assistant helping triage and manage alerts in the Keboola CRM.
This skill activates when the user wants to:
Determine which alert workflow the user needs:
crm alerts list # default = unacknowledged
crm alerts list --severity critical
crm alerts list --severity high
crm alerts list --type stale_deal
crm alerts list --alert-type checkin_overdue # alias of --type
crm alerts list --all --format human # include already acknowledged
--type (or its alias --alert-type) accepts a single value per call. Common CSM-relevant types: checkin_overdue, usage_threshold, eb_engagement_stale, champion_not_tested, stale_deal, incomplete_meddpicc, close_date_risk, no_progression, stalled, escalation. To triage a specific category for a CSM book, run e.g. crm alerts list --type checkin_overdue --format human.
A bundled --for-csm preset (one flag, multiple types) and a repeatable --alert-type (multiple types in one call) are requested by the CSM audit but not yet exposed by GET /api/alerts — see the NOTE block in crm alerts list --help. Until then, run the listing once per type or post-filter the JSON output with jq.
Alerts are categorized by severity:
| Severity | Meaning | Response Time |
|---|---|---|
| Critical | Immediate action required — deal at risk, major issue | Same day |
| High | Important — needs attention within 24-48 hours | 1-2 days |
| Medium | Notable — should be addressed this week | This week |
| Low | Informational — review when convenient | As needed |
For each alert, note:
crm alerts ack <alert_id>
Acknowledging an alert means:
After acknowledging, take the appropriate action based on alert type (see Step 6 for alert type reference).
crm alerts summary
The summary provides:
A structured morning triage routine:
Step 5a: Check critical and high alerts
crm alerts list
Review all Critical and High severity alerts first. For each:
Step 5b: Review alert summary
crm alerts summary
Check overall alert health:
Step 5c: Acknowledge handled alerts
crm alerts ack <alert_id>
Go through alerts you have already addressed and acknowledge them to keep the list clean.
Step 5d: Check pipeline for new risks
crm pipeline show
crm pipeline forecast
Cross-reference alerts with pipeline status:
Step 5e: Plan the day
Based on triage results, prioritize:
Common CRM alert types and recommended actions:
| Alert Type | Description | Recommended Action |
|---|---|---|
| Stalled Deal | Opportunity with no activity for 14+ days | Contact the customer, update CRM |
| Close Date Passed | Close date is in the past, deal still open | Update close date or close the deal |
| Stage Too Long | Deal stuck in a stage beyond expected duration | Review blockers, consider downstage |
| MEDDPICC Gap | Critical MEDDPICC component missing or incomplete | Schedule qualification meeting |
| No Champion | Opportunity lacks an identified champion | Prioritize champion development |
| No EB Engagement | Economic Buyer not yet engaged in Demo+ stage | Request EB meeting |
| Contract Expiring | Contract expires within 90 days, no renewal started | Initiate renewal conversation |
| Low Pipeline Coverage | Pipeline coverage below 2x quota gap | Increase prospecting activity |
| Large Deal Risk | High-ACV deal showing risk indicators | Conduct deal review |
| Activity Drop | Significant decrease in account activity | Re-engage customer contacts |
npx claudepluginhub keboola/crm-plugin --plugin keboola-crmGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.