Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

brave-headless

bởi kelexine

Web & Frontend Development
495Lượt tải do clawskills.sh công bố
2Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Headless web search and content extraction via the Brave Search API.

Mô tả

Kỹ năng này làm gì

Headless web search and content extraction using the Brave Search API. Runs as a CLI tool without a browser, returning search results and full page content as plain text or JSON. Includes retry logic, circuit breaking, and bounded parallel fetching.

Combines search and content extraction in one tool with production-grade fault tolerance, avoiding the overhead of running a full browser like Playwright or Puppeteer.

Khi nào nên dùng

  • Searching the web from an AI agent workflow
  • Extracting readable content from a URL for summarization
  • Piping search results into downstream scripts
  • Looking up documentation pages without a browser
  • Researching topics and collecting structured output

Quy trình ví dụ

ĐẦU VÀO

User asks: 'Find recent articles about WebAssembly and extract their content'

AGENT
  1. 1

    Runs search.js with the query and --content flag

  2. 2

    Brave Search API returns top results with URLs

  3. 3

    Content fetcher retrieves each page in parallel up to the concurrency limit

  4. 4

    Readability extracts main article text, converted to Markdown

  5. 5

    Results are printed as structured plain text or newline-delimited JSON

ĐẦU RA

Numbered results with title, URL, snippet, and extracted Markdown content for each page

Yêu cầu

  • BRAVE_API_KEY environment variable
  • Brave Search API account (free tier available at brave.com/search/api)

Cài đặt

clawhub install kelexine/brave-headless

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết