From work-workflow
Verify browser/UI state using API-first approach with browser fallback
How this skill is triggered — by the user, by Claude, or both
Slash command
/work-workflow:check-browser <question><question>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify browser/UI state efficiently using **API-first approach** when possible, falling back to browser automation only when visual verification is required.
Verify browser/UI state efficiently using API-first approach when possible, falling back to browser automation only when visual verification is required.
When you need to verify something in the browser (element exists, data status, counts), use this command to get a concise answer without filling up context.
PREFER API checks - Most data can be verified via API endpoints:
curl -s http://localhost:5175/api/queue-monitoring | jq '{totalQueues, operationalQueues, criticalQueues}'curl -s http://localhost:5175/api/services-status | jq '.summary'curl -s http://localhost:5175/api/incidents | jq '{total: .incidents | length}'Use browser automation ONLY for:
/check-browser <question>
/check-browser Is Queue Health showing all operational?
→ curl -s localhost:5175/api/queue-monitoring | jq '{total: .queueData.totalQueues, operational: .queueData.operationalQueues}'
/check-browser What color is the Queue Health card border?
→ Navigate to page, inspect specific element's computed style
For API-verifiable questions: Run curl command with jq to extract only the needed data. Return concise JSON.
For visual verification (rare):
Use mcp__playwright_headed__* tools with browser_evaluate to extract specific CSS values:
// Example: Get border color
document.querySelector('[data-testid="queue-health-card"]')?.style.borderColor
ANSWER: Yes, Queue Health is green - 20/20 queues operational
ANSWER: Border color is rgb(34, 197, 94) / green
| Check | API Endpoint | jq Filter |
|---|---|---|
| Queue Health | /api/queue-monitoring | `.queueData |
| Services | /api/services-status | .summary |
| Incidents | /api/incidents | {total: .incidents | length, open: [.incidents[] | select(.status=="open")] | length} |
| Dashboard | /api/dashboard | . |
npx claudepluginhub thomfilg/ai-plugin-work --plugin work-workflowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.