Obsidian skills
Obsidian Skills
Skills for agents working with Obsidian: Markdown with wikilinks, Bases, JSON Canvas, Obsidian CLI, Defuddle and Knap
Install
/plugin marketplace add kepano/obsidian-skills
/plugin install obsidian@obsidian-skillsThis is third-party code. Review the repository files before installing.
What it does
A set of skills that teach an agent to create and edit Obsidian files correctly. They cover Obsidian Flavored Markdown with wikilinks, embeds and callouts, Bases files with views and formulas, JSON Canvas, and vault operations through the Obsidian CLI. The defuddle skill extracts clean markdown from web pages to save tokens, and knap renders Markdown templates from JSON or CSV.
Who it is for. Obsidian users who connect an agent to their notes vault.
Good fit when
- The agent maintains notes in an Obsidian vault
- You need to build a Bases view or a Canvas
- You need to save a web article as clean markdown
- You are developing an Obsidian plugin or theme
Not a fit when
- Your notes live in Notion or another service rather than Obsidian
Example request
Create a meeting note in the vault with wikilinks to attendees and add it to the projects baseLimitations
The defuddle and obsidian-cli skills need their CLI tools installed. For OpenCode you must clone the whole repo, not just the skills folder.
How to disable. Remove the obsidian plugin in Claude Code, or delete the skills folder from .claude, ~/.codex/skills or ~/.opencode/skills.
Security check
- Skills call external CLIs: Obsidian CLI and defuddle
- Defuddle fetches web pages
README in short
A short README for a set of Agent Skills for Obsidian following the open spec. The skills work in Claude Code, Codex and OpenCode. It covers installation via the marketplace, npx skills and manual setup per agent. A table lists six skills.
SKILL.md
--- name: defuddle description: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly. --- # Defuddle Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage. If not installed: `npm install -g defuddle` ## Usage Always use `--md` for markdown output: ```bash defuddle parse <url> --md ``` Save to file: ```bash defuddle parse <url> --md -o content.md ``` Extract specific metadata: ```bash defuddle parse <url> -p title defuddle parse <url> -p description defuddle parse <url> -p domain ``` ## Output formats | Flag | Format | |------|--------| | `--md` | Markdown (default choice) | | `--json` | JSON with both HTML and markdown | | (none) | HTML | | `-p <name>` | Specific metadata property |
FAQ
Where do I put the skills for Claude Code manually?
In a .claude folder at the root of your Obsidian vault, or whichever folder Claude Code works in.
Related
Search tours, hotels, flights, trains and excursions via Aviasales, Travelata, Level.Travel, Tutu.ru, Tripster and Sputnik8
A skill pack for Yandex 360: Mail, Calendar, Contacts, Directory, Telemost, Disk, Forms and Tracker
Hosted MCP server for finding cheap round-trip flights across flexible dates, no key or signup
An unofficial Python client and skill for the SberMobile account: tariff, package balances, services and bonuses