Skip to main content
affpapa.org
RU EN
skill CX Codex

ops-investigate-alert — Claude Code skill: install and overview

Investigates production alerts end-to-end by collecting telemetry, error logs, and recent code diffs. Gives on-call engineers an evidence-based incident root cause.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add c0x12c/ai-toolkit --skill ops-investigate-alert -a claude-code
Open on GitHub

What ops-investigate-alert does

Alert triaging starts with an environment check. The skill inspects connected MCP servers for platforms like Datadog, Grafana, or PagerDuty. Without an active monitoring MCP server, the investigation stops immediately with an error. The user can pass either a direct monitor link or an alert name to begin.

The core procedure always gathers the monitor state, queries telemetry an hour around the incident, and pulls ERROR logs. When the GitHub CLI tool is authorized, the agent inspects the last two deployed tags to correlate exceptions with fresh commits. A Kubernetes MCP can also inspect pod health and OOM events.

The skill never pushes git tags or alters deployment states. Every run finishes with an inline breakdown containing evidence, diagnostic confidence, and targeted remediation steps.

What it helps with

  • investigate triggered monitoring alerts
  • correlate metric anomalies with application error logs
  • diff recent releases with GitHub CLI during incidents
  • inspect Kubernetes pod restarts near failure events

Example prompts for the agent

  • Investigate the high-memory-usage alert on the billing service
  • Check metrics and logs for the failing payment-gateway monitor
  • Analyze the auth-service-5xx alert and inspect recent code changes

How to install ops-investigate-alert

1Skills CLI (Vercel)

npx skills add c0x12c/ai-toolkit --skill ops-investigate-alert -a claude-code

2Manually: put the files in place

~/.claude/skills/ops-investigate-alert/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ops-investigate-alert/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ops-investigate-alert

How to install ops-investigate-alert in Claude Code?

Run npx skills add c0x12c/ai-toolkit --skill ops-investigate-alert -a claude-code. The skill writes its instructions to ~/.claude/skills/ops-investigate-alert/SKILL.md.

What does ops-investigate-alert do?

It queries telemetry systems through an MCP server, inspects errors in logs, and scans recent repository changes. The final output provides a root cause hypothesis alongside triage advice.

What prerequisites does ops-investigate-alert require?

You need at least one monitoring MCP server connected, such as Datadog MCP. Optional integrations include authenticated GitHub CLI for commit diffs and Kubernetes MCP for cluster health.

Similar skills

All skills for DevOps and infrastructure →
wizard Matt Pocock This skill creates an interactive bash wizard for manual setup steps, CI secrets, third-party dashboards, and one-off migrations. 553,369installs hyperframes-cli heygen-com Controls HyperFrames video workflows from the CLI: audits layouts and contrast, edits timeline clips, captures snapshots, and renders locally or in cloud runtimes. CX Codex +1 1,300,000installs setup-pre-commit Matt Pocock This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit. 489,289installs using-git-worktrees Jesse Vincent Prepares an isolated workspace before feature work or plan execution. It checks the repository first, then uses native worktree support or Git. CX Codex 217,153installs finishing-a-development-branch Jesse Vincent This skill checks the test suite and guides branch completion: merge locally, open a Pull Request, or leave the work in place. CX Codex 214,439installs orca-cli stablyai The skill lets an agent manage Orca worktrees, terminals, artifacts and the built-in browser through the orca CLI. Useful when your work already runs inside Orca. CX Codex +1 354,000installs

From the same set24

security-checklist Audits Micronaut/Kotlin backends for access control, input checks, injection risks, and data exposure. Use it during implementation or review. CX Codex +1 ★ 109repo stars python-testing-strategies A skill that tells your coding agent how to test FastAPI apps: pytest-asyncio, httpx AsyncClient, data factories and the checks every endpoint needs. CX Codex +1 ★ 109repo stars python-api-endpoint-creator Builds FastAPI endpoints and CRUD modules with separate router, service, and repository layers. Use it when adding a domain module and its tests. CX Codex +1 ★ 109repo stars ops-oncall-log Pulls alerts from your monitoring platform and writes a structured on-call log to the team wiki. Useful at the end of a shift or during a review. CX Codex +1 ★ 109repo stars market-research Research markets, competitors, funds, or technology with a structured workflow. Use the skill to gather evidence before testing a business idea or contacting an investor. CX Codex +1 ★ 109repo stars kotlin-best-practices A skill that pins down Kotlin conventions: null safety, Either instead of thrown exceptions, coroutines, and Exposed ORM patterns. Useful while writing or reviewing Kotlin. CX Codex +1 ★ 109repo stars investor-outreach Draft investor emails, introduction requests, follow-ups, and updates with help from this skill. Use it when reaching out to an angel, VC, or accelerator. CX Codex +1 ★ 109repo stars investor-materials A skill for producing investor-facing documents: a pitch deck, one-pager, memo and financial model. Useful when the numbers and the story have to line up across every file. CX Codex +1 ★ 109repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor