agent-browser-verify

작성자: openai

개발 서버를 위한 자동 브라우저 검증입니다. dev 서버가 시작되면 agent-browser로 시각적 기본 점검을 실행하여 페이지 로딩을 확인합니다…

npx skills add https://github.com/openai/plugins --skill agent-browser-verify

Dev Server Verification with agent-browser

You MUST verify the dev server with agent-browser after starting it. Do not assume the page works just because the dev server process started. Many issues (blank pages, hydration errors, missing env vars, broken imports) are only visible in the browser. Run this verification before continuing with any other work:

Quick Verification Flow

# 1. Open the dev server
agent-browser open http://localhost:3000
agent-browser wait --load networkidle

# 2. Screenshot for visual check
agent-browser screenshot --annotate

# 3. Check for errors
agent-browser eval 'JSON.stringify(window.__consoleErrors || [])'

# 4. Snapshot interactive elements
agent-browser snapshot -i

Verification Checklist

Run each check and report results:

  1. Page loads — agent-browser open succeeds without timeout
  2. No blank page — snapshot shows meaningful content (not empty body)
  3. No error overlay — no Next.js/Vite error overlay detected
  4. Console errors — evaluate document.querySelectorAll('[data-nextjs-dialog]') for error modals
  5. Key elements render — snapshot -i shows expected interactive elements
  6. Navigation works — if multiple routes exist, verify at least the home route

Error Detection

# Check for framework error overlays
agent-browser eval 'document.querySelector("[data-nextjs-dialog], .vite-error-overlay, #webpack-dev-server-client-overlay") ? "ERROR_OVERLAY" : "OK"'

# Check page isn't blank
agent-browser eval 'document.body.innerText.trim().length > 0 ? "HAS_CONTENT" : "BLANK"'

On Failure

If verification fails:

  1. Screenshot the error state: agent-browser screenshot error-state.png
  2. Capture the error overlay text or console output
  3. Close the browser: agent-browser close
  4. Fix the issue in code
  5. Re-run verification (max 2 retry cycles to avoid infinite loops)

Diagnosing a Hanging or Stuck Page

When the page appears stuck (spinner, blank content after load, frozen UI), the browser is only half the story. Correlate what you see in the browser with server-side evidence:

1. Capture Browser Evidence

# Screenshot the stuck state
agent-browser screenshot stuck-state.png

# Check for pending network requests (XHR/fetch that never resolved)
agent-browser eval 'JSON.stringify(performance.getEntriesByType("resource").filter(r => r.duration === 0).map(r => r.name))'

# Check console for errors or warnings
agent-browser eval 'JSON.stringify(window.__consoleErrors || [])'

# Look for fetch calls to workflow/API routes that are pending
agent-browser eval 'document.querySelector("[data-nextjs-dialog]") ? "ERROR_OVERLAY" : "OK"'

2. Check Server Logs

After capturing browser state, immediately check the backend:

# Stream Vercel runtime logs for the deployment
vercel logs --follow

# If using Workflow DevKit, check run status
npx workflow inspect runs
npx workflow inspect run <run_id>

# Check workflow health
npx workflow health

3. Correlate Browser + Server

Browser ShowsServer ShowsLikely Issue
Spinner / loading foreverNo recent function invocationsAPI route not being called — check fetch URL in client code
Spinner / loading foreverFunction started but no step logsWorkflow step is stuck — add console.log at step entry/exit
Blank page, no errorsBuild succeeded, no runtime errorsHydration issue or missing data — check SSR vs client rendering
Network request pending504 Gateway Timeout in logsFunction timeout — increase maxDuration or optimize step
Console: "Failed to fetch"OIDC/credential error in logsMissing vercel env pull — run vercel link && vercel env pull
Error overlay visibleStack trace in runtime logsRead the server error — it usually has more detail than the client

4. Fix and Re-verify

After fixing the issue:

# Re-open and verify the fix
agent-browser open http://localhost:3000
agent-browser wait --load networkidle
agent-browser screenshot after-fix.png
agent-browser eval 'document.body.innerText.trim().length > 0 ? "HAS_CONTENT" : "BLANK"'
agent-browser close

On Success

agent-browser close

Report: "Dev server verified — page loads, no errors detected, key UI elements render correctly."

Suggest Verification After Implementation

When you finish building or implementing a feature (wrote code, created routes, set up a project), briefly let the user know they can ask you to verify everything works with a browser check. One sentence is enough. Don't force it if only a small fix or question was involved.

openai의 다른 스킬

release
openai
커밋된 버전을 올리고, 이를 반영하고, 병합된 커밋에 태그를 단 후, Burrito 릴리스 워크플로우를 검증하여 Symphony 릴리스를 진행합니다. 다음과 같이 요청받았을 때 사용합니다…
signing-entitlements
openai
macOS 앱의 서명, 자격, 강화된 런타임 및 Gatekeeper 문제를 검사합니다. 코드 서명 실패, 누락된 자격 등을 진단하라는 요청을 받을 때 사용하세요.
building-ai-agent-on-cloudflare
openai
Cloudflare에서 Agents SDK를 사용하여 상태 관리, 실시간 WebSockets, 예약 작업, 도구 통합, 채팅을 통해 AI 에이전트를 구축합니다…
epigraphdb-skill
openai
온톨로지, 문헌, MR, 유전자-약물 및 지원 경로 증거에 대한 간결한 EpiGraphDB API 요청을 제출합니다. 사용자가 간결한 EpiGraphDB 요약을 원할 때 사용하세요.
runtime-behavior-probe
openai
런타임 동작 조사를 계획하고 실행하며, 임시 프로브 스크립트, 검증 매트릭스, 상태 제어, 결과 우선 보고서를 사용합니다. 다음 경우에만 사용하세요…
deep-security-scan
openai
사용자가 심층적이고, 철저하며, 다중 패스 또는 변동성을 줄이는 저장소 전체 또는 범위가 지정된 경로의 Codex Security 스캔을 요청할 때 사용합니다. 반복적으로 독립적인…
define-security-policy
openai
저장소 또는 구성 요소에 대한 SECURITY.md 지침을 정의, 검토 또는 업데이트합니다. 사용자가 Codex Security가 검토해야 할 대상과 범위를 벗어나는 항목을 명확히 하려 할 때 사용합니다…
validation
openai
Codex가 보안 스캔의 검증 단계에 이미 있거나 사용자가 하나 이상의 후보 보안 결과를 판별하도록 명시적으로 요청할 때 사용합니다…