ワンクリックで
agent-browser-debug
Browser debugging: execute JavaScript, view console output and page errors, record traces, and run performance profiling.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Browser debugging: execute JavaScript, view console output and page errors, record traces, and run performance profiling.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run forever as a resident worker in ONE Codex turn: every 5 minutes poll a watched directory for new task files and execute each one to completion, then keep watching — the turn never ends. Use when the user says "queue-loop", "무한 루프로 돌려", "큐 감시해서 계속 실행", "resident worker", "watch a directory and run new tasks forever", or wants a single invocation that keeps picking up dropped commands indefinitely. Because the work stays inside one already-running turn, it keeps issuing model requests across usage-limit windows (the workspace spend cap gates only NEW top-level turns, not an in-flight one). Do NOT use for a single one-shot task, or when the user wants the turn to finish and report back.
Use when the user wants Korean prose cleaned of AI tone, stiff old-fashioned (할아버지/훈장/공문서) tone, translationese, and excessive quotation marks - or asks to "글 다듬어", "자연스럽게", "AI 말투 제거", "할아버지 말투 빼", "deslop 한국어", or "writing-fixer". Removes as many AI and unnatural expressions as possible in one thorough pass while preserving meaning, code, math, and markup. Korean prose only.
Inject a task into the queue-loop worker's queue so a running Codex resident worker picks it up on its next poll (~5 min). Use when the user says "queue-submit", "큐에 작업 넣어", "task 주입해", "이거 워커한테 넘겨", "submit a task to the codex worker", "enqueue this for queue-loop", or wants to hand a job off to the always-on worker instead of doing it inline. It only writes a *.task file into the watched queue directory (default ~/codex-queue) — it does NOT run the task in this session. Do not use when the user wants the work done right now in the current session.
한국어 텍스트에서 AI가 쓴 흔적, 번역체, 부자연스러운 표현을 제거하고 자연스러운 한국어로 다시 써 주는 스킬. 말투 통일, 문장부호 교정, 피동 표현 정리, 영어 직역체 제거를 수행한다.
Iteratively review the current repository, plan fixes from the reviews, and implement the plans. Runs three prompts in strict order (deep review → plan from reviews → implement with ralph) and repeats the full three-prompt cycle up to N times (default 100). Context is cleaned between iterations by spawning each full cycle in a fresh subagent.
Browser configuration: viewport sizing, device emulation, geolocation, offline mode, color scheme, and HTTP settings.
| name | agent-browser-debug |
| version | 1.0.0 |
| description | Browser debugging: execute JavaScript, view console output and page errors, record traces, and run performance profiling. |
| allowed-tools | ["Bash","Read"] |
Run JavaScript, inspect console output, capture errors, and profile performance.
agent-browser eval "<js>" # Run JavaScript in page context
agent-browser eval -b "<base64>" # Run base64-encoded script
agent-browser eval --stdin # Read script from stdin
agent-browser console # View console messages (log, warn, info)
agent-browser console --clear # Clear console message buffer
agent-browser errors # View uncaught page errors
agent-browser errors --clear # Clear error buffer
agent-browser trace start [path] # Start recording trace
agent-browser trace stop [path] # Stop and save trace file
Trace files can be opened in Chrome DevTools (chrome://tracing).
agent-browser profiler start # Start CPU profiling
agent-browser profiler stop [path] # Stop and save profile
# Get the current user from app state
agent-browser eval "JSON.stringify(window.__STORE__.user)"
# Check for JavaScript errors on a page
agent-browser open https://example.com
agent-browser errors
# Monitor console output during interaction
agent-browser console
# Record a performance trace
agent-browser trace start /tmp/trace.json
# ... perform actions ...
agent-browser trace stop /tmp/trace.json
# Profile a slow operation
agent-browser profiler start
agent-browser click "#heavy-button"
agent-browser wait 5000
agent-browser profiler stop /tmp/profile.json
# Execute multi-line script via stdin
echo 'document.querySelectorAll("a").length' | agent-browser eval --stdin
eval for extracting app state or running custom assertionserrors after page load to catch JavaScript issuesconsole to monitor application logging during interactions/tmp/ for ephemeral debugging