Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

knowledge-base-collector

bởi reed1898

Web & Frontend Development
696Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Collect and organize a personal knowledge base from URLs (web/X/WeChat) and screenshots.

Mô tả

Kỹ năng này làm gì

Saves URLs and screenshots into a local knowledge base with tag-based classification. Supports web pages, X/Twitter links, and WeChat Official Account articles, with a macOS node fallback when WeChat cloud fetch is blocked. Entries are stored as markdown files with metadata and indexed for keyword and tag search.

The macOS node fallback for WeChat fetching achieves a higher success rate than standard scrapers, which typically hit verification blocks on WeChat content.

Khi nào nên dùng

  • Archive a WeChat article before it gets deleted or blocked
  • Save X/Twitter threads to a searchable personal library
  • Store a screenshot with OCR text as a tagged note
  • Search past saved links from Telegram by keyword or tag
  • Generate a weekly digest of recently saved content

Quy trình ví dụ

ĐẦU VÀO

User sends: https://mp.weixin.qq.com/s/example-article

AGENT
  1. 1

    Detect source type as WeChat from the mp.weixin.qq.com domain

  2. 2

    Attempt cloud fetch via r.jina.ai

  3. 3

    On verification block, delegate fetch to connected macOS node (e.g. Reed-Mac)

  4. 4

    Write content.md and meta.json to kb/20_Inbox/urls/<YYYY-MM>/<item>/

  5. 5

    Append entry to index.jsonl with assigned topic tags

ĐẦU RA

Article archived with tags like #wechat and #agent, searchable via Telegram

Cài đặt

clawhub install reed1898/knowledge-base-collector

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

Liên kết