Aller au contenu
TakoAPI
Retour aux skills

librarian

par nonlinear

Search & Research
326Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Conversational interface for semantic book search (companion skill for Librarian project)

Description

Ce que fait ce skill

A conversational interface for searching a personal book library using semantic embeddings. Ask questions in natural language and get back synthesized answers with page-level citations. Runs as a companion to the Librarian project via a three-layer architecture: AI skill, shell wrapper, and Python search engine.

Returns precise citations with page and paragraph numbers from local files instead of summarizing from memory or requiring a web search.

Quand l'utiliser

  • Finding what a specific author says about a topic across your library
  • Locating passages in a single book by concept or keyword
  • Getting cited answers from a topic folder of books
  • Cross-referencing ideas across multiple texts without opening each file
  • Querying a personal research archive by natural language

Exemple de workflow

ENTRÉE

User asks: What does Graeber say about the origins of money?

AGENT
  1. 1

    Load .library-index.json and .topic-index.json metadata

  2. 2

    Match query against known book titles and topic IDs to infer scope

  3. 3

    Build shell command: ./librarian.sh "origins of money" topic finance 5

  4. 4

    Parse JSON results from Python search engine

  5. 5

    Synthesize answer and format citations with page numbers

SORTIE

Paragraph summarizing Graeber's argument with inline citations like [Debt: The First 5000 Years, p.21, ¶2] and a sources list

Prérequis

  • Librarian parent project installed (github.com/nonlinear/librarian)

Installation

clawhub install nonlinear/librarian

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens