Pular para o conteúdo
TakoAPI
Voltar às skills

semfind

por paperboardofficial

Coding Agents & IDEs
356Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Semantic search over local text files using embeddings.

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

ENTRADA

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

AGENTE
  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

SAÍDA

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

Instalação

clawhub install paperboardofficial/semfind

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links