Your reliability workflow,
one command away

Deploy monitors, manage incidents, and run checks from the terminal you already live in.

Start for free Book a demo

Trusted to keep `test`, `staging`, and `prod` running

Terminal

$ npx checkly skills

Get all the information and context to let your agent initialize,

set up, create, test and manage your monitoring checks using the Checkly CLI.

Examples:

$ checkly skills initialize

$ checkly skills configure

$ checkly skills configure api-checks

$ checkly skills investigate

$ checkly skills investigate checks

$ checkly skills communicate

$ checkly skills communicate incidents

Actions:

initialize

Learn how to initialize and set up a new Checkly CLI project from scratch.

configure

Learn how to create and manage monitoring checks using Checkly constructs and the CLI.

Read the docs

Agent Guardrails

Write commands (create, update, resolve, deploy) implement a confirmation protocol designed for agent safety. When an agent runs a write command, the CLI returns exit code 2 with a JSON envelope.

Skills

Give your agents the context they need directly from the CLI. Add skills to recursively use the most up-to-date docs, expertise, and examples.

CI/CD Native

Run checks as part of your deployment pipeline. Catch regressions on every deploy, before they reach production.

“Checkly CLI has enhanced our engineering team's ability to quickly build, validate and deploy an entire suite of checks from their local development environment.”

Tavares Chambless

Manager, Quality Assurance - Loyal Health

See it in action

A real Claude Code session, from alert to pushed fix, using the Checkly CLI to investigate failures, declare an incident, and ship the fix in minutes.

Book a demo

claude

Model: Opus 4.6 (1M cont…◑ medium · /effort

Run npx checkly init in your project. From there you can write checks as code, run them with npx checkly test, and ship them with npx checkly deploy.

Deploy monitors, run checks, and manage incidents without opening the Checkly UI. Everything you deploy is defined in code that lives in your repo.

Write commands (create, update, resolve, deploy) follow a confirmation protocol built for agents. When an agent runs one, the CLI returns exit code 2 with a JSON envelope describing the change, so nothing happens until it is confirmed.

Yes. Run your checks as a step in your deployment pipeline and catch regressions on every deploy, before they reach production.

Ready to leave the dashboard behind?

Install the Checkly CLI and bring your entire monitoring workflow into the terminal.

Start for free Read the docs

Your reliability workflow, one command away

Trusted to keep test, staging, and prod running