web-pilot
liranudi 제작
Web & Frontend Development요약
Search the web and read page contents without API keys.
설명
이 스킬이 하는 일
Web browsing toolkit built on four Python scripts. Searches via DuckDuckGo, Brave, or Google across multiple pages, reads page text, runs interactive browser sessions with tab management and click support, and downloads files including PDFs. No API keys required.
Works without any API keys or account signups, using Playwright and Chromium directly to access real browser behavior including cookie banner dismissal.
사용 시점
- Scraping search results from DuckDuckGo without an API key
- Extracting readable text from a paywalled or cookie-gated page
- Taking a full-page screenshot of a site for visual reference
- Downloading a PDF and pulling its text content automatically
- Navigating a multi-tab session to compare content across pages
예시 워크플로
User asks: find recent articles about LLM context windows and summarize the top result
- 1
Run google_search.py with the query and --pages 2 to get a result list
- 2
Pick the top URL from the returned JSON
- 3
Run read_page.py on that URL with --format markdown
- 4
Parse the markdown output and extract the main article text
- 5
Return a summary to the user
Markdown text of the article, ready for summarization
설치
clawhub install liranudi/web-pilotCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.