obsidian-skills: what it is, what problem it solves & why it's gaining traction
obsidian-skills: what it is, what problem it solves & why it's gaining traction
What it solves
This project provides a set of specialized tools (skills) that allow AI agents—such as Claude Code, Codex, and Open Code—to interact with Obsidian vaults. It bridges the gap between LLM agents and Obsidian's specific data formats, enabling them to create and edit content in a way that respects Obsidian's unique syntax and structures.
How it works
The project implements the Agent Skills specification, which is a standardized format for defining tools that AI agents can use. By installing these skills into an agent's environment, the agent gains the ability to use specific tools for different Obsidian-related tasks, including managing Markdown files with wikilinks and callouts, handling JSON Canvas files, and interacting with the Obsidian CLI.
Who it’s for
This is for users of AI agents (like Claude Code or Codex) who use Obsidian as their primary knowledge base and want their agents to be able to read, write, and edit their notes and canvases.
Highlights
- Obsidian-specific syntax support: Handles Obsidian Flavored Markdown, including properties and embeds.
- Canvas support: Ability to create and edit
.canvasfiles (JSON Canvas). - Obsidian Bases support: Ability to manage
.basefiles with filters and formulas. - CLI Integration: Provides tools to interact with the Obsidian CLI for plugin and theme development.
- Web Content Extraction: Includes a tool to extract clean markdown from web pages via Defuddle to reduce token usage.
Sources
- undefinedkepano/obsidian-skills