Persona + Skills Pack

A senior on-call engineer for your AI coding assistant.

Senior On-Call Engineer for Claude Code, Cursor, Windsurf

A senior on-call engineer persona plus five Anthropic Agent Skills that produce paste-ready reliability deliverables. Evidence first, ranked hypotheses, UTC timestamps, rollbacks included, specific commands with expected output.

Get DevOps / SRE Persona + Skills Pack — $39 one-timeSee pricing

Works with Claude Code natively. Cursor, Windsurf, Codex CLI, GitHub Copilot, Cline, Continue.dev, Zed, Amazon Q through CxMS Pro AI’s MCP bridge.

Sound familiar?

4:12 AM. PagerDuty buzzes. The pod is in CrashLoopBackOff. You paste kubectl describe into your AI and it tells you to “try deleting the pod and see if it comes back.” You have seen this exact failure mode before. Three months ago. OOMKilled on a Tuesday, same service. The postmortem from that incident is in a Notion page somewhere, the action item is still open, and your AI has no idea.

You write the postmortem yourself by 6 AM because someone has to. You review a terraform plan at 10 AM that is about to destroy a production database because someone renamed an identifier “for consistency.” You dig up a runbook from six months ago with half the commands pointing to a dashboard URL that moved three quarters back.

Incidents compound. Your AI does not.

What this is (and what it is not)

The DevOps / SRE Persona + Skills Pack is a zip of Anthropic Agent Skills (SKILL.md files with frontmatter). It is not a monitoring tool. It is not an MCP server. It is not a replacement for PagerDuty, Datadog, or your observability stack.

Loaded into Claude Code’s skills directory, it is a senior on-call engineer voice plus five production skills: Postmortem Writer, Kubernetes Debugger, Terraform Reviewer, Runbook Generator, SLO Drafter. Loaded into CxMS Pro AI, the persona becomes memory-aware. Incident history persists. Action items stay linked to the postmortem that spawned them. Runbooks remember which steps actually worked last time.

It does not replace your senior SRE. It is the first-pass draft a senior edits instead of writing at 5 AM.

What you get

Ship tomorrow's postmortem while the incident is still fresh

The Postmortem Writer reads an incident transcript and produces a Google SRE blameless postmortem: roles not names, UTC timestamps, confirmed vs. suspected contributing factors, quantified impact, action items with owners and dates. You edit a 90% draft at 6 AM instead of writing from scratch.

Debug CrashLoopBackOff with ranked hypotheses, not a grab-bag

The Kubernetes Debugger reads your kubectl describe and logs, ranks hypotheses by likelihood, proposes one verification step at a time, and ships a specific fix for each hypothesis across the top production Kubernetes failure patterns (EKS, GKE, AKS, and self-hosted).

Stop the terraform plan about to destroy your database

The Terraform Reviewer reads a plan diff and emits severity-tagged output (BLOCK, WARN, INFO). Never approves an unexpected destroy. Never writes 'LGTM' on a plan with blocking issues. Flags the fifteen patterns that actually cause production incidents.

Make runbooks the next on-call can follow at 3 AM

The Runbook Generator turns a PagerDuty alert into an executable runbook. Every step a specific command with expected output. Every fix with a rollback. Written like the author actually got paged at 2 AM.

Turn 'it should be fast' into a real SLO

The SLO Drafter produces SLI definition, SLO target with rationale, error budget policy, and multi-window burn-rate thresholds, Sloth-compatible YAML.

One opinionated SRE voice, not five disagreeing subagents

A senior on-call engineer persona curated from the Google SRE Book, the Google SRE Workbook, Charity Majors' observability primers, and canonical IaC patterns.

Works with your tools

Works natively with Claude Code. Unzip into ~/.claude/skills/opencxms-persona-devops-sre/ and Claude Code picks it up on next launch.

Works with Cursor, Windsurf, Codex CLI, GitHub Copilot, Cline, Continue.dev, Zed, and Amazon Q Developer through CxMS Pro AI’s MCP bridge.

Standalone: the pack drops in and runs today. No memory engine required.

With CxMS Pro AI: the persona carries incident history. The AI remembers what broke last time, the postmortem action items, the SLO decisions. Institutional on-call memory that survives personnel changes.

Claude Code
Cursor
Windsurf
Codex CLI
GitHub Copilot
Cline
Continue.dev
Zed

Who this is for

  • ✓Priya, on-call rotation owner at a 40-person engineering org. Got paged at 4 AM Thursday. Needs the postmortem before Monday standup.
  • ✓Marcus, platform engineer. Staring at a CrashLoopBackOff with two minutes of logs and a screaming Slack channel.
  • ✓Ana, senior SRE. Reviewing a terraform plan at 10 AM after someone 'cleaned up naming.' 80% sure it is about to destroy a production database.
  • ✓Tom, team lead inheriting a service with six-month-old runbooks. Wants runbooks that assume the reader just got paged and knows nothing about this system.
  • ✓Leah, engineering manager. Has 'the API should be fast' as a stated reliability goal. VP wants an SLO by next sprint.

Pricing

DevOps / SRE Persona + Skills Pack
$39 one-time

Single-seat perpetual license

7-day money back guarantee. No questions asked.

Get on Gumroad
Want persistent AI memory too? Add CxMS Pro for $49 one-time, or grab the Complete Bundle at $199.

FAQ

Does the DevOps / SRE Persona + Skills Pack require CxMS Pro AI?
No. The pack is Anthropic Agent Skills. Drop it into Claude Code's skills directory and it works. CxMS Pro AI is the persistent-memory upgrade, not a prerequisite.
Why is this pack $39 instead of $29?
Deeper reference material (SRE Book, observability primers, IaC canonical patterns) and skills that cover more ground per invocation. Terraform Reviewer reads entire plans. Postmortem Writer reads entire incident transcripts.
Does the Kubernetes debugging skill cover my specific distribution?
The K8s Debug skill covers general Kubernetes patterns that apply across managed services (EKS, GKE, AKS) and self-hosted clusters.
Can the Terraform Reviewer catch provider-specific issues?
Yes, for the major providers (AWS, Azure, GCP, Cloudflare). Obscure providers may need additional context in the prompt.
Will the incident transcripts or code I paste leave my machine?
No. The pack is local files. Your AI tool's model calls are whatever you configured them to be. Nothing in the pack phones home.
What's the refund policy?
7-day money back guarantee. No questions asked. Packs are static files with no license check, so there is no deactivation step.

Stop re-teaching your AI every morning.

One purchase. Perpetual license. Seven-day money-back guarantee.

Get the DevOps / SRE Pack on Gumroad

Built by OpenCxMS Technologies, Inc. — a Pennsylvania Public Benefit Corporation.