Obsidian Cli logo

Obsidian Cli

Community
kv0906
obsidian-cli

Control Obsidian from the terminal using the `obsidian` CLI. Use when the agent needs to open notes, search the vault inside Obsidian, append/prepend content to the active file, create notes from templates, manage properties, check backlinks/orphans, query Bases, or interact with the running Obsidian app. Requires Obsidian 1.12+ running.

Overview

Publisherkv0906
Repositorypm-kit
Skill nameobsidian-cli
Stars
140
Forks
35
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kv0906 on GitHub. Read the source before you install it.

Installation

Install the Obsidian Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kv0906/pm-kit/tree/main/.claude/skills/obsidian-cli
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kv0906/pm-kit.git /tmp/pm-kit
mkdir -p .claude/skills
cp -r /tmp/pm-kit/.claude/skills/obsidian-cli .claude/skills/obsidian-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Obsidian Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Obsidian Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Obsidian Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Obsidian CLI Skill

Control the running Obsidian app from the terminal. Supplementary tool alongside Read/Write/Edit, Glob, Grep, QMD, and Neo4j.

Prerequisites

  • Obsidian 1.12+ running (early access, Catalyst license)
  • CLI registered: Settings > General > Command line interface
  • Templates plugin: Settings > Core Plugins > Templates > Template folder → _templates
  • PATH: /Applications/Obsidian.app/Contents/MacOS (in ~/.zprofile)

Important: Noisy Output

The CLI outputs Loading updated app package... to stdout on every invocation. Always filter with grep -v:

bash
obsidian orphans total 2>/dev/null | grep -v "Loading updated"    # correct — clean output
obsidian orphans total                                             # noisy output in agent context

Shorthand for all examples below: 2>/dev/null | grep -v "Loading updated" is abbreviated as 2>/dev/null for readability, but always include the full filter in practice.

When to Use CLI vs File Tools

ScenarioUse CLIUse File Tools
Open a note in Obsidian UIobsidian openNo equivalent
Read/write file contentEither worksPrefer Read/Write/Edit
Search vault contentobsidian searchPrefer Grep/QMD
Open today's daily note in Obsidianobsidian dailyNo equivalent
Append task to daily noteobsidian daily:appendEither
Create note from templateobsidian create template=XManual template apply
Check backlinks/orphans/unresolvedobsidian backlinks/orphansManual grep
Set/read properties (frontmatter)obsidian property:setEdit tool
Query a Base viewobsidian base:queryNo equivalent
Execute Obsidian commandsobsidian commandNo equivalent

Rule of thumb: CLI for Obsidian-app-specific actions (open files, trigger commands, query Bases, graph relationships). File tools for direct file manipulation.

Agent Integration Patterns

Keeper — Supplementary Health Checks

bash
# Quick vault health stats (supplement Python/Neo4j checks)
obsidian unresolved verbose 2>/dev/null | grep -v "Loading updated"
obsidian orphans total 2>/dev/null | grep -v "Loading updated"
obsidian deadends total 2>/dev/null | grep -v "Loading updated"

Scribe — Quick Capture

bash
# Fast append to daily note (no file path needed)
obsidian daily:append content="- [ ] Review TPM progress" silent 2>/dev/null

# Atomic frontmatter update
obsidian property:set name=status value=shipped path="prd/xmarket/checkout.md" 2>/dev/null

# Template-based note creation
obsidian create name="New PRD" template=prd silent 2>/dev/null

# Surface created note in Obsidian
obsidian open path="decisions/xmarket/2026-02-11-payment-provider.md" newtab 2>/dev/null

Scout — Fallback Search

bash
# Backlinks via Obsidian's graph (alternative to Neo4j)
obsidian backlinks file=Note 2>/dev/null

# Quick text search (alternative to QMD)
obsidian search query="payment provider" 2>/dev/null

Today — Workflow Touchpoints

bash
# Phase 0: Ensure daily note visible in Obsidian
obsidian daily silent 2>/dev/null

# Phase 3: Quick health stats
obsidian unresolved total 2>/dev/null
obsidian orphans total 2>/dev/null

# Phase 5: Surface daily note
obsidian open path="daily/2026-02-11.md" 2>/dev/null

Command Reference

Vault & File Targeting

bash
# Auto-detects vault from CWD
obsidian daily 2>/dev/null

# Target specific vault
obsidian vault=Notes daily 2>/dev/null

# By name (wikilink resolution)
obsidian read file=Recipe 2>/dev/null

# By exact path
obsidian read path="prd/xmarket/checkout.md" 2>/dev/null

Daily Notes

bash
obsidian daily 2>/dev/null                              # Open today's daily note
obsidian daily:read 2>/dev/null                         # Read daily note contents
obsidian daily:append content="- [ ] Task" 2>/dev/null  # Append to daily note
obsidian daily:prepend content="## Morning" 2>/dev/null # Prepend after frontmatter
obsidian daily:append content="text" silent 2>/dev/null # Append without opening

Files & Folders

bash
obsidian files 2>/dev/null                        # List all files
obsidian files folder=prd 2>/dev/null             # List files in folder
obsidian files ext=md total 2>/dev/null           # Count .md files
obsidian open file=Note 2>/dev/null               # Open a file
obsidian open file=Note newtab 2>/dev/null        # Open in new tab
obsidian create name="New Note" 2>/dev/null       # Create file
obsidian create name=Note template=prd 2>/dev/null  # Create from template
obsidian create name=Note content="text" silent overwrite 2>/dev/null
obsidian read file=Note 2>/dev/null               # Read file contents
obsidian append file=Note content="new line" 2>/dev/null
obsidian prepend file=Note content="top line" 2>/dev/null
obsidian move file=Note to="archive/" 2>/dev/null
obsidian delete file=Note 2>/dev/null             # Trash (recoverable)

Search

bash
obsidian search query="meeting notes" 2>/dev/null          # Search vault
obsidian search query="TODO" path=daily 2>/dev/null        # Search in folder
obsidian search query="bug" total 2>/dev/null              # Count matches
obsidian search query="fix" matches 2>/dev/null            # Show match context
obsidian search query="test" format=json 2>/dev/null       # JSON output

Links & Graph

bash
obsidian backlinks file=Note 2>/dev/null           # Backlinks to a file
obsidian backlinks file=Note counts 2>/dev/null    # With link counts
obsidian links file=Note 2>/dev/null               # Outgoing links from a file
obsidian unresolved 2>/dev/null                    # Broken/unresolved links
obsidian unresolved verbose 2>/dev/null            # Include source files
obsidian orphans 2>/dev/null                       # Files with no incoming links
obsidian orphans total 2>/dev/null                 # Count orphans
obsidian deadends 2>/dev/null                      # Files with no outgoing links

Properties (Frontmatter)

bash
obsidian properties file=Note 2>/dev/null                  # List properties
obsidian properties all counts 2>/dev/null                 # All vault properties
obsidian property:read name=status file=Note 2>/dev/null   # Read a property
obsidian property:set name=status value=done file=Note 2>/dev/null  # Set a property
obsidian property:set name=tags value="[a,b]" type=list file=Note 2>/dev/null
obsidian property:remove name=old_prop file=Note 2>/dev/null

Tags

bash
obsidian tags all counts 2>/dev/null              # All tags with counts
obsidian tags file=Note 2>/dev/null               # Tags in a file
obsidian tag name=project verbose 2>/dev/null     # Tag info with file list

Tasks

bash
obsidian tasks 2>/dev/null                         # Tasks in active file
obsidian tasks daily 2>/dev/null                   # Tasks from daily note
obsidian tasks daily todo 2>/dev/null              # Incomplete daily tasks
obsidian tasks all todo 2>/dev/null                # All incomplete tasks
obsidian task daily line=3 toggle 2>/dev/null      # Toggle a daily task

Bases

bash
obsidian bases 2>/dev/null                         # List all .base files
obsidian base:query file=MyBase format=json 2>/dev/null     # Query base
obsidian base:query file=MyBase view=TableView format=csv 2>/dev/null

Templates

bash
obsidian templates 2>/dev/null                     # List templates
obsidian template:read name=prd 2>/dev/null        # Read template
obsidian template:insert name=prd 2>/dev/null      # Insert into active file

Workspace & Tabs

bash
obsidian tabs 2>/dev/null                          # List open tabs
obsidian workspace 2>/dev/null                     # Show workspace tree
obsidian workspace:load name=Writing 2>/dev/null   # Load workspace

Commands

bash
obsidian commands 2>/dev/null                      # List all command IDs
obsidian command id=editor:toggle-bold 2>/dev/null # Execute a command

Common Patterns for This Vault

Quick daily task capture

bash
obsidian daily:append content="- [ ] Review TPM progress" silent 2>/dev/null

Check vault health via CLI

bash
obsidian orphans total 2>/dev/null
obsidian unresolved verbose 2>/dev/null
obsidian deadends total 2>/dev/null

Open a PRD in Obsidian

bash
obsidian open path="prd/tpm/private-market-mvp-phases.md" 2>/dev/null

Find all notes tagged with a project

bash
obsidian tag name=xmarket verbose 2>/dev/null

Query a Base for structured data

bash
obsidian base:query file=Projects format=json 2>/dev/null

Frequently asked questions

What does the Obsidian Cli AI skill do?

Control Obsidian from the terminal using the `obsidian` CLI. Use when the agent needs to open notes, search the vault inside Obsidian, append/prepend content to the active file, create notes from templates, manage properties, check backlinks/orphans, query Bases, or interact with the running Obsidian app. Requires Obsidian 1.12+ running.

Why use Obsidian Cli on TypingMind?

Because you install it once and use it with any model. Obsidian Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Obsidian Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kv0906/pm-kit/tree/main/.claude/skills/obsidian-cli. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Obsidian Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Obsidian Cli?

As many as you like. As long as a model supports skills, you can use Obsidian Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Obsidian Cli AI skill free?

Yes. It is published on GitHub by kv0906 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇