Sign inGet started
Skills

Run skills on a schedule

View as MarkdownOpen in ChatGPTOpen in Claude
Connect your agent
Add to CursorAdd to VS Code

Allow scheduled skills on your Claude Code once: a cloud routine with a token, or a one-line hourly check.

Updated

We run no AI on your data, so your scheduled skills run on your own Claude Code, once you allow it. Runs use your Claude limits. A teammate's skill never runs on your Claude Code, and yours never runs on theirs.

This is the one-time part. Once it's done, skills run on their own and write when they find something.

Before you start

  • Required: the tag on your site, and your agent connected. See Quickstart.
  • Required: a skill with a schedule in Skills. The Weekly check-up runs on Mondays at 09:00 once added.

1. Allow schedules on your Claude Code (Required)

Open Skills and switch on Allow on my Claude Code under Schedules run on. Until you allow it and set it up, your scheduled skills say Paused.

2. Set up the routine (Required)

Choose one. We recommend the token:

WayHow it runsRun now
With a token (Recommended)A routine in Claude's cloud, on time, with your laptop closedYes
Quick setupChecks for work once an hour; a run starts within the hour after it's dueNo

With a token: open Routines in Claude, make a routine named nextanalytica with our prompt and the nextanalytica connector, add an API trigger and paste its address and token into the setup window. A test run checks it.

Quick setup: paste one line into Claude Code in the terminal or at claude.ai/code. There it becomes a routine in the cloud. In the Claude desktop app the same line makes a task on that computer, which runs only while the app is open.

3. Watch the first run

Skills shows Your Claude Code under Schedules run on once the routine works. The first finding comes when a skill finds something worth your attention. A quiet week writes nothing, and that's normal.

Next step

How a run works

Related
  • Skills security: What a scheduled analytics run can read and do, whose Claude Code runs it, what it can never touch and the limits that keep your website safe.
  • Skills: Skills are instructions your agent follows on demand or on a schedule. They tell you what changed and what to fix, and stay quiet otherwise.
  • How a run works: A scheduled run, step by step: it starts, reads context and numbers, reports a finding or stays quiet and finishes.
  • Anatomy of a finding: One finding from start to fix, told as a story: our rule notices wasted ad spend, a skill runs and explains it, and a person decides what to change.
  • Project knowledge: The team's instructions, goals and memory your agent reads before every answer and every run, who writes them, the limits and how agents add to them.
  • Steer skills: Shape what skills look at and how they report, with team instructions, a skill's own text and feedback.
Still have questions?
Was this page useful?