Sign inGet started
Skills

Skills FAQ

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

Skeptical questions about skills: why bother, what they can touch, who runs and pays for them and whether they miss things.

Updated

Why can't I ask my agent each time instead?

You can, and should for one-off questions. A skill is for the question you'd ask every Monday: it runs without you and writes only when there's something to say. Asking by hand every week rarely survives a busy month.

What can a skill actually touch?

Less than you'd think. It reads one project's data and reports. It never changes your website, code or tools, and never acts through a connector. See Skills security.

Do you train AI on my data?

No. We run no model; your own Claude does the work, and we never use your data to train one.

How are skills different from alerts?

Our rules are the alerts: one fixed pattern, checked once a day after the day before closes. A skill reads the context, explains what changed and proposes the fix. See Insights.

Won't it flood my inbox?

No. A run posts at most one finding, and a later one on the same subject updates it. A dismissed subject stays quiet for you for 30 days.

Won't a skill miss things?

It sees what your data holds and what its instructions ask for, nothing more. Name what matters in the instructions, and connect the sources a skill needs. A quiet run isn't a miss: it means nothing crossed the bar.

Who pays for the runs?

The person who scheduled them: their skills run on their own Claude Code, on their Claude plan, and use their Claude limits. nextanalytica itself is free with 30 days of history.

Keep exploring

Related
  • Skills troubleshooting: Why scheduled skills say Paused, why a routine stopped running, why findings don't arrive and what to do when a finding is wrong, answered step by step.
  • 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.
  • Run skills on a schedule: Allow scheduled skills on your Claude Code once: a cloud routine with a token, or a one-line hourly check.
  • 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.
  • 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.
Still have questions?
Was this page useful?