> AI agents: this is one page of nextanalytica's docs. The full index for agents: https://nextanalytica.app/llms.txt

# Skills FAQ

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

Updated: 2026-11-18

## 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](/docs/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](/docs/skills/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

- [Skills](/docs/skills)
- [Built-in skills](/docs/skills/built-in)

Canonical address: https://nextanalytica.app/docs/skills/faq
