zettel-builder

Transform raw material into atomic notes with explicit links and YAML frontmatter.

58|6|Updated May 21, 2026
One-click install
npx skills add https://github.com/wshuyi/zettel-builder --skill zettel-builder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: zettel-builder
Source: https://github.com/wshuyi/zettel-builder/tree/main
Command: npx skills add https://github.com/wshuyi/zettel-builder --skill zettel-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, fastembed, embed_lite, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates turning scattered material into a bottom-up Zettelkasten card network by atomizing content, restating core values, and establishing explicit links, enabling durable, readable knowledge growth.

Core Features & Use Cases

  • Atomization: break long content into individual, standalone cards that stay comprehensible over time.
  • Value restatement and linking: rewrite each card to express a clear stance with a justification and link rationale.
  • Four invocation modes: ingest, scan, inspect, write to cover from material intake to drafting outlines.
  • Clustering and deep research: periodic discovery of ready clusters, detection of gaps, and optional deep-research handoffs.
  • End-to-end workflow: automated card generation, de-duplication, and structured output with git-backed versioning.

Quick Start

Ingest a sample material with the /zettel ingest command to create atomic cards and start the value-restatement workflow.

Frequently Asked Questions about zettel-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate note-taking to build a connected knowledge graph from raw text and URLs?

To automate note-taking into a knowledge graph, you can atomize raw text, files, and URLs into standalone cards, restate their core values, and establish explicit links. This process enforces YAML frontmatter discipline and applies embedding clustering to organize the card network.

What is the zettelkasten method for atomizing content into a self-growing card network?

The zettelkasten method for atomizing content breaks long material into individual, standalone cards that remain comprehensible over time. It rewrites each card to express a clear stance with justification and link rationale, enabling durable, bottom-up knowledge growth.

How do I ingest chat fragments and files for clustering and value restatement?

You ingest chat fragments and files by processing them into atomic notes with value restatement and explicit linking. The system applies embedding clustering to discover ready clusters, detect gaps, and prepare the ingested sources for deep-research handoffs.

Can I use fastembed and numpy for deduplication and versioned git push in a knowledge management workflow?

Yes, you can use fastembed and numpy to support embedding and clustering within an end-to-end knowledge management workflow. This enables automated card generation, deduplication, structured artifact management, and versioned git push for the output.

What is the best way to assess readiness and detect gaps in a bottom-up zettelkasten?

The best way to assess readiness and detect gaps in a bottom-up zettelkasten is through periodic clustering and deep research. The system discovers ready clusters across diverse sources and optionally hands off gaps for further investigation.