Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

backboard

bởi chrisk60331

Web & Frontend Development
1.8kLượt tải do clawskills.sh công bố
3Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Integrate Backboard.io for assistants, threads, memories.

Mô tả

Kỹ năng này làm gì

Connects to Backboard.io through a local Flask backend to manage AI assistants, conversation threads, persistent memories, and document RAG. Supports uploading PDFs, DOCX, spreadsheets, and code files for retrieval within conversations.

Keeps assistant state, memories, and document indexes in a single local backend rather than managing them across separate services.

Khi nào nên dùng

  • Storing user preferences that persist across chat sessions
  • Uploading internal docs and querying them in conversation
  • Creating purpose-specific assistants for different teams
  • Reviewing conversation history across multiple threads
  • Accumulating project context as memories over time

Quy trình ví dụ

ĐẦU VÀO

User asks: 'Upload my project spec and tell me what it covers'

AGENT
  1. 1

    Call backboard_upload_document with the file path

  2. 2

    Poll backboard_document_status until processing completes

  3. 3

    Call backboard_send_message with memory set to Auto to query the indexed document

  4. 4

    Return the summary to the user

ĐẦU RA

Document indexed and summary returned based on retrieved content

Yêu cầu

  • Backboard.io API key set as BACKBOARD_API_KEY environment variable
  • Local Flask backend running on http://localhost:5100, started via ./start.sh in the backend directory

Cài đặt

clawhub install chrisk60331/backboard

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

Liên kết