Obsidian Yaml Frontmatter logo

Obsidian Yaml Frontmatter

Community
jykim
obsidian-yaml-frontmatter

Manage YAML frontmatter properties with consistent formatting, property names, and value types. Use when creating or updating frontmatter in markdown files.

Overview

Publisherjykim
Repositoryclaude-obsidian-skills
Skill nameobsidian-yaml-frontmatter
Stars
52
Forks
10
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 jykim on GitHub. Read the source before you install it.

Installation

Install the Obsidian Yaml Frontmatter 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/jykim/claude-obsidian-skills/tree/main/obsidian-yaml-frontmatter
  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/jykim/claude-obsidian-skills.git /tmp/claude-obsidian-skills
mkdir -p .claude/skills
cp -r /tmp/claude-obsidian-skills/obsidian-yaml-frontmatter .claude/skills/obsidian-yaml-frontmatter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Obsidian Yaml Frontmatter 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 Yaml Frontmatter 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 Yaml Frontmatter 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.

YAML Frontmatter Management

Standardize YAML frontmatter properties across all vault content.

When to Use This Skill

Activate when you need to:

  • Add or update frontmatter in markdown files
  • Ensure consistent property naming and formatting
  • Format tags, dates, or other property values
  • Validate frontmatter structure

Note: This skill manages frontmatter PROPERTIES (keys, values, types, formatting). For document STRUCTURE (heading hierarchy, section order, frontmatter position), use obsidian-markdown-structure skill.

Core Frontmatter Rules

1. Single YAML Block at Top

Structure:

yaml
---
property: value
---

## First Section Header

Critical Rules:

  • One YAML block at top of file
  • Blank line after closing ---
  • No content before first heading (after frontmatter)

2. Standard Property Names

Use lowercase, consistent keys:

yaml
✅ CORRECT:
title: Document Title
created: 2025-10-31
tags:
  - tag1
source: https://example.com
author: Author Name

❌ INCORRECT:
Title: Document Title (capitalized)
date: 2025-10-31 (use "created" not "date")
tag: tag1 (use "tags" plural)

No Duplicate Properties:

  • Use created (not both date and created)
  • Use tags (not both tag and tags)

3. Tag Formatting

CRITICAL: Plain text in YAML, NO hashtags:

yaml
✅ CORRECT:
tags:
  - journal
  - daily
  - reflection

❌ INCORRECT:
tags:
  - #journal
  - #daily

Always use list format with dashes:

yaml
✅ CORRECT (list format):
tags:
  - tag1
  - tag2

❌ INCORRECT (inline):
tags: [tag1, tag2]

4. Date Format

Use YYYY-MM-DD consistently:

yaml
✅ CORRECT:
created: 2025-10-31
updated: 2025-11-01

❌ INCORRECT:
created: 10/31/2025
created: 2025-10-31T10:30:00

5. Link Lists

Wrap wiki links in quotes:

yaml
✅ CORRECT:
sources:
  - "[[Journal/2025-10-31]]"
  - "[[Articles/2025-10-31 Title]]"

links:
  - "[[Roundup/2025-10-31]]"

attendees:
  - "[[People/John]]"
  - Jane

❌ INCORRECT:
sources:
  - [[Journal/2025-10-31]] (missing quotes)

6. Quote Values with Special Characters

Quote values containing: : # " or numeric-looking strings

Single quote wrapping (easiest for values with "):

yaml
✅ CORRECT:
title: 'He said, "Hello."'
note: 'It\'s called "PKM".'

Double quote wrapping with escaping:

yaml
✅ CORRECT:
title: "He said, \"Hello.\""
source: "https://example.com"
version: "2.0"

Literal double-quote character:

yaml
✅ CORRECT:
quote_char: '"'

Mixed quotes preference: Use double quotes, escape only " (single quotes don't need escaping):

yaml
✅ CORRECT:
note: "It's called \"PKM\"."

❌ INCORRECT:
title: AI Era: Thriving Framework (unquoted colon)
version: 2.0 (parsed as number, not string)

Multiline values (no escaping needed):

yaml
✅ CORRECT:
description: |
  He said, "Hello."
  New line preserved.

Standard Property Set

Core Properties (All Content)

yaml
---
title: Document Title
created: YYYY-MM-DD
tags:
  - category
  - type
---

Content with Sources

yaml
---
title: Article Title
created: YYYY-MM-DD
source: https://url or file path
author: Author Name
tags:
  - clipping
  - topic
---

Relational Content

yaml
---
title: Document Title
created: YYYY-MM-DD
tags:
  - category
sources:
  - "[[Source File 1]]"
  - "[[Source File 2]]"
links:
  - "[[Related Topic]]"
---

Events/Meetings

yaml
---
title: Meeting Name
created: YYYY-MM-DD
event_date: YYYY-MM-DD
attendees:
  - "[[Person 1]]"
  - Person 2
sources:
  - "[[Journal/YYYY-MM-DD#Section]]"
tags:
  - meeting
  - event
---

Workflow

Step 1: Determine Content Type

  • Daily content (Journal, Notes)
  • Ingested content (Clippings, Articles)
  • Created content (Analysis, Tasks, Events)
  • Topic/Project pages

Step 2: Select Property Set

  • Core properties (title, created, tags)
  • Add source/author if applicable
  • Add relational links (sources, links, attendees)
  • Add content-specific properties

Step 3: Format Values

  • Dates: YYYY-MM-DD format
  • Tags: Plain text list (no #)
  • Links: Quoted wiki links
  • Special chars: Quote values with : or #

Step 4: Structure Check

  • Single YAML block at top
  • Blank line after ---
  • Consistent property names (lowercase)
  • No duplicate properties

Quality Checklist

Before completing frontmatter:

  • Single YAML block at top with blank line after
  • All property keys lowercase and consistent
  • Tags are plain text (NO hashtags)
  • Dates in YYYY-MM-DD format
  • Wiki links wrapped in quotes
  • Special characters quoted appropriately
  • No duplicate properties (created vs date, tags vs tag)

Frequently asked questions

What does the Obsidian Yaml Frontmatter AI skill do?

Manage YAML frontmatter properties with consistent formatting, property names, and value types. Use when creating or updating frontmatter in markdown files.

Why use Obsidian Yaml Frontmatter on TypingMind?

Because you install it once and use it with any model. Obsidian Yaml Frontmatter 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 Yaml Frontmatter in TypingMind?

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

Which AI models can use Obsidian Yaml Frontmatter?

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 Yaml Frontmatter?

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

Is the Obsidian Yaml Frontmatter AI skill free?

Yes. It is published on GitHub by jykim 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 👇