Help us improve
Share bugs, ideas, or general feedback.
Unifies notifications across GitHub, Linear, desktop alerts, hooks, and communication surfaces into one ECC-native workflow for alert routing, deduplication, escalation, and inbox collapse.
npx claudepluginhub affaan-m/ecc --plugin eccHow this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:unified-notifications-opsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the real problem is not a missing ping. The real problem is a fragmented notification system.
Polls GitHub notifications and handles items that dedicated workflows miss — fork PR comments, cross-repo mentions, and stale unanswered items. Runs on a schedule.
Creates Sentry alerts via the workflow engine API. Supports email, Slack, PagerDuty, and Discord notification actions with configurable trigger events and conditions.
Configures Rootly workflows for automated incident response, including triggers like incident_created, conditions like severity_gte, and actions like create_slack_channel or create_jira_ticket.
Share bugs, ideas, or general feedback.
Use this skill when the real problem is not a missing ping. The real problem is a fragmented notification system.
The job is to turn scattered events into one operator surface with:
Start from what already exists:
Prefer ECC-native orchestration over telling the user to adopt a separate notification product.
Treat the lane as:
The goal is fewer, better notifications.
| Class | Examples | Default handling |
|---|---|---|
| Critical | broken default-branch CI, security issue, blocked release, failed deploy | interrupt now |
| High | review requested, failing PR, owner-blocking handoff | same-day alert |
| Medium | issue state changes, notable comments, backlog movement | digest or queue |
| Low | repeat successes, routine churn, redundant lifecycle markers | suppress or fold |
If the workspace has no severity model, build one before proposing automation.
List:
Call out what ECC already owns.
For each event family, answer:
Use these defaults:
Look for:
Prefer:
For each real notification need, define:
If ECC already has the primitive, prefer:
End with:
CURRENT SURFACE
- sources
- channels
- duplicates
- gaps
EVENT MODEL
- critical
- high
- medium
- low
ROUTING PLAN
- source -> channel
- why
- operator owner
CONSOLIDATION
- suppress
- merge
- canonical summaries
NEXT ECC MOVE
- skill / hook / agent / MCP
- exact workflow to build next
project-flow-ops when the root cause is backlog / PR coordination rather than alertsworkspace-surface-audit when the user first needs a source inventoryworkspace-surface-auditproject-flow-opsgithub-opsknowledge-opscustomer-billing-ops when the notification pain is billing/customer operations rather than engineering