9 skills for devops
Cloudflare Workers errors and usage
Every morning: requests, error rate and CPU time per Cloudflare Worker for the last 24 hours, against the same day last week, with the top exceptions.
DevelopersEvery day at 8:00Report cardUses Cloudflare.Railway deploys and usage
Every morning: Railway deployments that failed or crashed since yesterday, with the error lines, plus usage so far and the estimated bill for the cycle.
DevelopersEvery day at 8:00Report cardUses Railway.AWS cost anomaly alert
Every morning: new AWS cost anomalies with the service, account, region and dollars above expected, and a question about who owns each one.
DevOpsEvery day at 9:00Asks youUses AWS.Datadog monitors in alert
Every hour of the working day: Datadog monitors in Alert or Warn, how long each has been there, and what is new or recovered since the hour before.
DevOpsHourly, 8:00 to 18:00 on weekdaysReport cardUses Datadog.n8n failed executions report
Every morning: n8n workflows with failed executions since yesterday, how many times each failed, the error message and the node it stopped on.
DevOpsEvery day at 8:00Report cardUses n8n.Grafana firing alerts digest
Every morning: Grafana alert rules that are firing or pending, grouped by folder, with how long each has fired and which are silenced.
DevOpsEvery day at 8:30Report cardUses Grafana.Azure daily cost report
Every morning: yesterday's Azure cost against the 7-day average, with the top services and resource groups and the one that moved.
DevOpsEvery day at 8:00Stat tileUses Azure.Snowflake credit usage this week
Every Monday: Snowflake credits used in the last 7 days against the week before, by warehouse, with the most expensive queries and who ran them.
Data teamsMondays at 8:00Stat tileUses Snowflake.Databricks failed jobs
Every morning: Databricks job runs that failed or timed out since yesterday, with the failing task, the error line and a link, and an ask about repairing.
Data teamsEvery day at 7:30Asks youUses Databricks.What an agent can take off devops’s plate
The DevOps morning is a tour: the cost dashboard, the alerting tool, the CI page, the incident list, the uptime report. Each one shows everything it knows, and none of them says what is new since yesterday or what needs an owner.
These skills each answer one of those questions. Yesterday's AWS or Azure spend with the service behind a jump, cost anomalies with their dollar impact, Datadog monitors in Alert and Grafana rules firing, failed pipelines on main in GitLab or Azure DevOps, Cloudflare Workers errors, PagerDuty incidents by service, n8n workflows that failed and UptimeRobot uptime for the month. Your agent runs them on a schedule with read-only credentials, posts one card per question and only pings you when something changed.
Other teams
One board for every report devops runs
Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.
Free during the open beta. No card.