Skip to main content
Agent Skills are an open standard supported by many AI agents and coding assistants including Claude Code, Cursor, OpenAI Codex, and others. Skills are reusable and modular capabilities for AI agents. They provide procedural knowledge that helps agents accomplish Checkly tasks more effectively. Think of Checkly Skills as an extension of your AI agent that enhances it with Checkly specific best practices and capabilities.

​
Installation

Use the Checkly CLI skills command to install Checkly skills globally or in your project: 
npx checkly skills install

# or if you prefer the `skills` CLI

npx skills add checkly/checkly-cli
After installation, restart your AI agent to load the skills.

​
Usage

Now when your agent needs to perform a Checkly-related task, it can automatically pull in the relevant context and use the provided instructions and resources to execute the task effectively.
Claude Code Example
❯ Can you create a new URLMonitor with Checkly for example.com?

⏺ Skill(checkly)
  ⎿ Successfully loaded skill · 3 tools allowed

⏺ Let me read more references and check the existing project structure

⏺ Bash(npx checkly skills configure)
⏺ Bash(npx checkly skills configure url-monitors)

⏺ Searched for 1 pattern, executed 2 commands

⏺ I'll create a new URLMonitor for example.com!

​
Examples

The Monitoring as Code workflow is by default AI-native because LLMs are excellent at writing and editing Checkly constructs code and modern AI agents can execute CLI commands easily. Provide the necessary Checkly context and let your AI agent of choice do the rest.

Create new checks, alert channels or other constructs

“Can you set up a new BrowserCheck for example.com?”

Bulk-update your monitoring resources

“Can you change all checks to run every 5 minutes instead of every 10 minutes?”

Gather information about alerts and your monitoring setup

“I just received an alert. Can you tell me details about the failing checks?”

Handle and communicate incidents

“Can you please open an incident and investigate a fix?”
Using Checkly, you can now control your monitoring setup with AI agents without needing a specific MCP server or API for your monitoring. Tell your agent what you want to do and it will access the necessary context and use the CLI to manage your monitoring setup effectively.

​
Skill Details

Create and manage monitoring checks, alert channels, dashboards, status pages, and other Checkly constructs using the CLI.Invoke explicitly:
npx checkly skills configure
Example prompts:
  • “Create a URL monitor for api.example.com that checks every 5 minutes”
  • “Set up a browser check that logs into my app and verifies the dashboard loads”
  • “Add a Slack alert channel for my production check group”
CLI usage:
# List all configure sub-actions
npx checkly skills configure

# Get reference for a specific check type
npx checkly skills configure api-checks
npx checkly skills configure browser-checks
npx checkly skills configure url-monitors

# Other constructs
npx checkly skills configure alert-channels
npx checkly skills configure check-groups
npx checkly skills configure supporting-constructs
Access check status, analyze failures, trigger on-demand runs, and debug errors across your monitoring setup.Invoke explicitly:
npx checkly skills investigate
Example prompts:
  • “Show me which checks are currently failing”
  • “Investigate why the login browser check started failing yesterday”
  • “Trigger an on-demand run of my API health check”
CLI usage:
# Get full investigate reference
npx checkly skills investigate

# Check inspection and on-demand runs
npx checkly skills investigate checks
Open and manage incidents and lead customer communications via status pages.Invoke explicitly:
npx checkly skills communicate
Example prompts:
  • “Create a new incident for the API outage and post it to the status page”
  • “Update the current incident with a resolution message”
  • “List all open incidents”
CLI usage:
# Get full communicate reference
npx checkly skills communicate

# Incident lifecycle management
npx checkly skills communicate incidents
Understand your account plan, entitlements, feature limits, and available monitoring locations.Invoke explicitly:
npx checkly skills manage
Example prompts:
  • “What features are available on my current Checkly plan?”
  • “Which monitoring locations can I use?”
  • “Check if my plan supports private locations”
CLI usage:
# Get full manage reference
npx checkly skills manage

# Check plan details and entitlements
npx checkly skills manage plan

​
Additional resources