By jasonsie
transform unstructured text into structured Zettelkasten notes with metadata and links
Run Firecrawl CLI commands — scrape, crawl, map, search, or agent
Create a Zettelkasten note from a Notion page via MCP integration
Promote a query answer or synthesis into a permanent Zettelkasten note. Files valuable explorations back into the vault.
Complete pipeline from any source (URL, text, file) to an integrated Zettelkasten literature note
Run semantic health checks on the vault — contradictions, staleness, orphans, missing pages, concept gaps. Use /vault-lint <path> [--fix]
Create, convert, or enhance diagrams using Unicode box-drawing characters and ASCII art
Distill layer of the 3-stage Zettelkasten pipeline. Takes the discover-layer output from zettelkasten-agent plus source content, classifies note_mode (atom vs thesis per ADR-0002), and produces the mode-appropriate conceptual model artifact (atom: one-line definition + optional why/boundary/code; thesis: executive summary + themes + optional appendix) plus mental model with modality hint, spinoff candidates, and a mode-aware char-budget self-check for obsidian-formatter-agent to assemble.
Update existing vault notes with backlinks and cross-references when a new note is ingested. Enriches the knowledge graph by connecting new content to existing notes.
Render diagrams for Zettelkasten notes. Honors the Image > ASCII > Mermaid > Structural Bullets priority chain; consumes a modality_hint from conceptual-modeler-agent
Extract content from URLs, text, or transcripts and produce structured Markdown files
Standardized bash terminal color formatting for agent output. Use when creating or updating agent prompts that need colored terminal output for progress indicators, success/error messages, file paths, or structured logging. Provides consistent color palette and usage patterns across all agents.
Auto-maintained vault catalog at .claude/index.md grouping all notes by domain with enriched metadata and a Keyword Index for fast retrieval. Use when you need to rebuild index, update index, or generate a vault catalog.
Semantic health checks for the Obsidian ZK vault. Detects contradictions between notes, stale content, orphan pages, missing pages, weak links, concept gaps, and cross-reference gaps. Use when the user asks to "lint the vault", "check vault health", "find contradictions", "find orphans", or "what's missing". Goes beyond structural compliance (vault-audit) to check semantic coherence.
Search the Obsidian Zettelkasten vault for notes matching a natural language query. Uses a tiered retrieval system: fast index lookup (Tier 0) → synthesis dedup (Tier 0.5) → grep-based fallback (Tiers 1-3). Works from any working directory. Use when you need to find related notes, check what exists on a topic, or gather context before creating new notes.
Clip a web page into a clean Markdown file under raw/, with images downloaded locally to raw/attachments/. Self-contained — depends only on the defuddle npm package installed inside this skill folder. Use when given a URL and asked to capture it for the vault without firecrawl or API keys.
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A Claude Code plugin that transforms unstructured content (URLs, videos, raw text) into structured Zettelkasten literature notes for Obsidian vaults.
zkfy automates the process of converting web content, YouTube videos, and raw text into well-structured Zettelkasten literature notes:
INPUT → [VIDEO TRANSCRIPTION] → MARKDOWN GENERATION → ANALYSIS → FORMATTING → CROSS-POLLINATION → INDEX + LOG → OUTPUT
zk-note skill — 4-agent Hybrid Atom/Thesis pipeline (zettelkasten-agent → conceptual-modeler-agent → diagram-agent → obsidian-formatter-agent) plus spinoff backlog write.claude/log.md and update .claude/index.md| Operation | Command | Description |
|---|---|---|
| Ingest | /source-to-zk | Source → note → cross-pollinate → log + index |
| Query | /query-to-note | Search vault → synthesize → file as permanent note → cross-pollinate → log |
| Lint | /vault-lint | Detect contradictions, orphans, stale content, concept gaps → auto-fix option → log |
note_mode (atom vs thesis per ADR-0002), produces mode-appropriate artifact (atom: one-line definition + optional Why/Boundary/Code; thesis: executive summary + theme chapters + optional appendix), emits mental model + spinoff candidates, self-validates mode-aware char budgetMode: atom | thesis frontmatter, filename, navigation, MOC updates, file writing.claude/log.md with structured entries.claude/index.md grouped by domainYour Obsidian vault must contain these folders:
your-vault/
├── cs/ # Computer Science notes
├── web/ # Web development notes
├── ai/ # AI/ML notes
├── principle/ # Principle notes
├── devops/ # DevOps notes
├── math/ # Math notes
├── 000.Index/ # Maps of Content (MOCs)
├── row/ # Source staging area
└── .claude/ # Auto-created by plugin
├── log.md # Operation log (wiki-log skill)
└── index.md # Vault catalog (vault-index skill)
# Clone the repository
git clone https://github.com/jasonsie/zkfy.git
cd zkfy
# Link to Claude Code plugins directory
ln -s "$PWD" ~/.claude/plugins/zkfy
# Create required prompt files
mkdir -p ~/.claude/prompts
touch ~/.claude/prompts/crawler.prompt.md
touch ~/.claude/prompts/obsidian-note.prompt.md
Create these prompt files with your formatting rules:
npx claudepluginhub jasonsie/zkfy --plugin zkfyAI thinking partner for your Obsidian vault — process, recall, synthesize, research with evidence-backed learning science
Turn your Markdown vault into a searchable knowledge graph that any AI agent can query.
Persistent, compounding knowledge base maintained by LLMs in Obsidian — agent-first edition. Four task-oriented agents (Researcher / Advisor / Curator / Scribe) with citations, confidence, supersession, and rolling session cache. Inspired by Karpathy's LLM Wiki pattern.
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
Import Zotero literature into Obsidian, optionally parse PDFs with MinerU, and preserve stable literature notes.
Sync AI conversations to an Obsidian knowledge base with Memory Mason knowledge base skills.