Fix Vale alerts

When to use this

The user asks to run Vale, fix its output, or make a lint job pass.

Do not trigger on prose edits alone. Editing a Markdown file is not a request to lint the repository, and an unasked-for wave of style changes buried in someone else's pull request is worse than the alerts.

Prerequisites

Check these before doing any work, and stop with a plain message if one fails:

1. vale --version succeeds. If not, use the setup skill.
2. A config exists — vale ls-config resolves without error.
3. The working tree is clean, or the user has said it is fine to branch from what is there.
4. You know which files to process. Ask if the user did not say.