vrt-check
Installation
SKILL.md
VRT Check
Run visual regression tests, then triage every failure by eye before touching a snapshot. The workflow's only real risk is rubber-stamping --update on a diff nobody looked at: everything below exists to prevent that.
Step 1: Discover the tooling
Never assume a command. Different repos wire VRT through different tools. Look for, in order:
| Order | Tool | Look for |
|---|---|---|
| 1 | Task runner targets | just --list or `grep -E 'visual |
| 2 | package.json scripts | grep -A2 '"scripts"' package.json for chromatic, test:visual, storybook:test, playwright test.*visual |
| 3 | Storybook test-runner | Presence of .storybook/test-runner.ts or @storybook/test-runner in package.json |
| 4 | Playwright screenshot tests | toHaveScreenshot( calls in *.spec.ts, or a playwright.config.* with snapshotDir/toMatchSnapshot settings |
| 5 | Chromatic | chromatic.config.json or a chromatic devDependency; these run in CI and produce a web UI, not local diff images. Say so and point the user there instead of trying to fake a local diff. |
| 6 | Loki | .loki config or loki devDependency |
Base each check on the actual output of the command you ran (ls, grep, just --list), never assert a file is absent without having listed the directory. If two of these are present, ask the user which one is authoritative rather than running both. If none are found, stop and say so, do not invent a screenshot workflow.