MCP App StoreMCP App Store
from llm-obsidian-wiki12
Implements Karpathy's LLM Wiki pattern: an LLM-maintained Obsidian vault that captures sources, synthesizes typed notes, and provides citation-backed queries fo
LLM Obsidian Wiki turns an LLM into a persistent researcher by maintaining a structured Obsidian vault. The skill automates capture of URLs, PDFs, GitHub content and transcripts, ingests raw sources into typed markdown pages (concepts, decisions, comparisons), and keeps the vault current with cross-links and confidence scores. Agents can then answer queries by reading the compiled wiki instead of re-scraping sources.
Use when you need durable, auditable memory for long-running projects: engineering ADRs, competitive research, annotated bibliographies, team knowledge bases, or any workflow where repeated context must be preserved and reused. It triggers on instructions to scaffold a vault, capture URLs/PDFs, ingest sources, or query the wiki.
Designed for Claude Code / Claude-like plugin environments and any agent that can manage a local filesystem and run the included utilities. It favors file-based workflows (Obsidian) over remote services.
Implements Karpathy's LLM Wiki pattern as a Claude Code plugin with four agent personas (Researcher, Advisor, Curator, Scribe) maintaining a structured Obsidian vault. 27 shell scripts cover capture (git log, GitHub, PDF, text, URL, YouTube), vault management (init, create page, promote draft, update index/hubs/hot), health checks (orphans, stale pages, contradictions, source drift, tree topology), and search/browse. Scripts are well-written with consistent error handling, umask 077, SSRF protection, and privacy-first defaults. Failed to run in audit env due to missing lib/ sourced files and external tool dependencies — expected for interactive vault tools.
obsidian-cliyt-dlpdefuddle-clipandoctrafilaturagh-cliImpressively comprehensive skill with strong security practices (umask 077 everywhere, SSRF validation, GraphQL injection prevention, no hardcoded creds, privacy-first defaults). Scripts are well-structured and portable (BSD/GNU date handling). The main limitation is tight coupling to Obsidian CLI and the lib/ shared modules — not a quality issue but affects portability.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c