Saltar al contenido
TakoAPI
Volver a skills

zettel-link

por hxy9243

Search & Research
363Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

This skill maintains the Note Embeddings for Zettelkasten, to search notes, retrieve notes, and discover.

Descripción

Qué hace esta skill

Maintains semantic embeddings for an Obsidian vault to enable note search, retrieval, and connection discovery. Uses cosine similarity to find related notes across a Zettelkasten. Supports local (Ollama) and cloud (OpenAI, Gemini) embedding providers.

Semantic search finds conceptually related notes even when they share no keywords, which keyword search and manual tagging cannot do.

Cuándo usarla

  • Finding notes related to a half-remembered idea
  • Discovering unexpected links between research notes
  • Rebuilding broken connections after reorganizing a vault
  • Searching notes by meaning rather than exact keywords
  • Generating a graph of semantically connected notes

Flujo de trabajo de ejemplo

ENTRADA

User asks: find notes related to 'epistemology and belief formation'

AGENTE
  1. 1

    Run config.py to confirm config/config.json exists

  2. 2

    Run embed.py --input <vault_dir> to generate or update the embedding cache

  3. 3

    Run search.py --input <vault_dir> --query 'epistemology and belief formation'

  4. 4

    Read search results from .embeddings/search_results.json

  5. 5

    Return the top matching note titles and snippets to the user

SALIDA

List of the 5 most semantically similar notes with similarity scores

Requisitos

  • Ollama installed locally with mxbai-embed-large model pulled (if using local provider)
  • OPENAI_API_KEY environment variable (if using OpenAI provider)
  • GEMINI_API_KEY environment variable (if using Gemini provider)

Instalación

clawhub install hxy9243/zettel-link

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces