メニュー
Query page content: get text, HTML, attributes, element state, accessibility snapshots, and find elements by role, text, label, placeholder, or testid.
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-query |
| version | 1.0.0 |
| description | Query page content: get text, HTML, attributes, element state, accessibility snapshots, and find elements by role, text, label, placeholder, or testid. |
| allowed-tools | ["Bash","Read"] |
Extract information from pages and locate elements.
agent-browser get text <sel> # Get text content of element
agent-browser get html <sel> # Get innerHTML
agent-browser get value <sel> # Get input/textarea value
agent-browser get attr <sel> <attr> # Get specific attribute value
agent-browser get title # Get page title
agent-browser get url # Get current URL
agent-browser get count <sel> # Count matching elements
agent-browser get box <sel> # Get bounding box {x, y, width, height}
agent-browser get styles <sel> # Get computed CSS styles
agent-browser is visible <sel> # Check if element is visible
agent-browser is enabled <sel> # Check if element is enabled
agent-browser is checked <sel> # Check if checkbox/radio is checked
agent-browser snapshot # Full accessibility tree with refs
agent-browser snapshot -i # Include invisible elements
agent-browser snapshot -C # Compact output
agent-browser snapshot -c # Include children details
agent-browser snapshot -d # Include descriptions
agent-browser snapshot -s # Include states
All find commands take an <action> (click, fill, type, etc.) and optional [value].
agent-browser find role <role> <action> [value] # By ARIA role (--name, --exact)
agent-browser find text <text> <action> # By visible text (--exact)
agent-browser find label <label> <action> [value] # By associated label
agent-browser find placeholder <ph> <action> [value] # By placeholder text
agent-browser find alt <text> <action> # By alt text (images)
agent-browser find title <text> <action> # By title attribute
agent-browser find testid <id> <action> [value] # By data-testid attribute
agent-browser find first <sel> <action> [value] # First matching element
agent-browser find last <sel> <action> [value] # Last matching element
agent-browser find nth <n> <sel> <action> [value] # Nth matching element (0-based)
# Get the page title
agent-browser get title
# Check if login button is visible
agent-browser is visible "button.login"
# Click the submit button by role
agent-browser find role button click --name "Submit"
# Fill email field by label
agent-browser find label "Email" fill "user@example.com"
# Get accessibility tree for page understanding
agent-browser snapshot -C
snapshot to understand page structure before interactingfind role, find label) over CSS selectors--exact flag enables exact text matching (default is substring)