sg-visual-run

Installation
SKILL.md

/sg-visual-run — Execute Visual Tests

Execute YAML test manifests using agent-browser (Playwright CLI). Hybrid execution: mechanical steps run directly, complex assertions delegate to LLM evaluation.

Recommended model: Sonnet 4.6. This skill runs scripted steps (click, fill, screenshot) + lightweight LLM assertions. Opus 4.7 provides no measurable quality gain here. Use /model sonnet before invoking to save Opus weekly quota.

Invocations

Command Behavior
/sg-visual-run Interactive — asks what to test
/sg-visual-run <text> Natural language — figures out what tests to run
/sg-visual-run --from-audit Run tests for impacted_ui_routes from audit-results.json
/sg-visual-run --diff=main Run tests impacted by changes since main
/sg-visual-run --all Full suite (skip interactive menu)
/sg-visual-run --regressions Re-run tests that failed last run

For full flag parsing rules, interactive/natural-language/audit flows, and route-to-manifest matching: see references/invocation-modes.md.

Related skills

More from bacoco/shipguard

Installs
1
GitHub Stars
5
First Seen
Apr 28, 2026