메뉴
Open a URL in headed Chromium and extract title, meta, main text, and links. Markdown + JSON. Use when page content must be live, not invented.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Headed Chromium CDP CLI: tabs, navigate, click/type, extract, screenshots, optional captcha hold helper. Use for general page exploration when a one-verb skill is not enough. Not Puppeteer/Playwright.
Fill form fields on an allowlisted host. Requires --allow-host and --fields. Never submits unless --submit. Redacts password-like values in output.
Multi-turn Google AI Mode via headed Chromium. Initial query uses udm=50; --follow-up / --turns for more turns. Prefer aim-google-ai for single-shot.
Google Search AI Mode (udm=50) via headed Chromium. Returns answer text and sources as markdown + JSON. Use for AI Mode answers, not classic blue links.
Google News (tbm=nws) via headed Chromium. Headlines, sources, times as markdown + JSON. Live only.
Classic Google web results (udm=14), not AI Mode. Ranked titles, URLs, snippets as markdown + JSON. Live only.
| name | aim-page-fetch |
| description | Open a URL in headed Chromium and extract title, meta, main text, and links. Markdown + JSON. Use when page content must be live, not invented. |
npm run page-fetch -- "https://example.com"
npm run page-fetch -- --screenshot /tmp/page.png --url "https://example.com"
Defaults: minimized, stop after session (--keep-open to chain).
JSON fields: title, url, canonical, description, meta, mainText, links[], rawLength, optional screenshot, optional cached.
Parse markdown, then ---JSON---. Prefer this over guessing page text.