Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

semfind

bởi paperboardofficial

Coding Agents & IDEs
356Lượt 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

Semantic search over local text files using embeddings.

Mô tả

Kỹ năng này làm gì

semfind searches text files by meaning rather than exact pattern, using local embeddings (BAAI/bge-small-en-v1.5 + FAISS) via the terminal. It works offline with no API keys. Install with `pip install semfind`.

Covers the gap where grep returns nothing because the search term and the stored text use different words for the same concept.

Khi nào nên dùng

  • Finding a past error in logs when you don't remember the exact wording
  • Searching project notes for a concept discussed weeks ago
  • Locating relevant memory files by topic rather than keyword
  • Recovering a decision or rationale buried in documentation
  • Scanning multiple markdown files for semantically related content

Quy trình ví dụ

ĐẦU VÀO

User asks: find any notes about database connection problems in memory files

AGENT
  1. 1

    Run grep first: grep "database connection" memory/*.md

  2. 2

    Grep returns no results

  3. 3

    Run semfind: semfind "database connection problems" memory/*.md -k 5

  4. 4

    Review results with similarity scores to identify relevant files

  5. 5

    Return matched lines and their similarity scores to the user

ĐẦU RA

memory/2026-01.md:42: Postgres refused connections after restart (0.831)

Cài đặt

clawhub install paperboardofficial/semfind

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

Liên kết