# vale-run

Run Vale (a prose/style linter) against an already-configured project and interpret its results.

## What it does

This skill covers invoking the `vale` CLI against files or directories, choosing an output format (human-readable CLI, `line`, or machine-parseable `JSON`), filtering by severity via `--minAlertLevel`, and handling exit codes in scripts and CI. It also covers resolving common runtime issues: false positives, format-specific inline suppression, and CI failures caused solely by Vale's non-zero exit code. It assumes the project already has a working `.vale.ini` and installed styles — setting those up is the sibling `vale-config` skill's job.

## Usage

```
/vale-run
```

Describe what you want to lint and how (human-readable output, CI/JSON output, filtered by severity). The skill will pick the right flags and, if results include false positives, walk through the narrowest applicable fix.

## Files

| File | Purpose |
|------|---------|
| `SKILL.md` | Core invocation, key flags, output format guidance, false-positive triage order |
| `references/troubleshooting.md` | Inline suppression syntax, rule-specific disabling, spelling ignore lists, pre-commit integration, CI edge cases |
| `references/sources.md` | Research provenance |