agentleFS
claude-office-skillsclaude-office-skills/skills/obsidian-automation/SKILL.md

Obsidian Automation

Skill433 starsChanged 10 months agoMITView on GitHub

Automate Obsidian knowledge management, note linking, and personal knowledge base workflows

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Consistent Naming: Use conventions

    line 251
  2. Distinctive:

    Tags vs Links: Use both strategically

    line 255

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Obsidian Automation

Automate Obsidian knowledge management and personal knowledge base workflows.

Core Capabilities

Note Creation

note_templates:
  daily_note:
    filename: "{{date:YYYY-MM-DD}}"
    folder: "Daily Notes"
    template: |
      # {{date:dddd, MMMM D, YYYY}}
      
      ## Morning Intentions
      - [ ] 
      
      ## Tasks
      - [ ] 
      
      ## Notes
      
      ## Evening Reflection
      
      ---
      [[{{date:YYYY-MM-DD|-1d}}|← Yesterday]] | [[{{date:YYYY-MM-DD|+1d}}|Tomorrow →]]

  meeting_note:
    filename: "Meeting - {{title}} - {{date}}"
    folder: "Meetings"
    template: |
      ---
      date: {{date}}
      attendees: {{attendees}}
      tags: meeting
      ---
      
      # {{title}}
      
      ## Agenda
      
      ## Notes
      
      ## Action Items
      - [ ] 
      
      ## Follow-ups
      
      [[Meetings MOC]]

Smart Linking

auto_linking:
  rules:
    - pattern: "[[Person/{{name}}]]"
      trigger: "@{{name}}"
      create_if_missing: true
      
    - pattern: "[[Project/{{project}}]]"
      trigger: "#proj/{{project}}"
      
  backlink_suggestions:
    enabled: true
    min_mentions: 2
    
  alias_support:
    - "[[Machine Learning|ML]]"
    - "[[Artificial Intelligence|AI]]"

Dataview Queries

dataview_examples:
  tasks_due_today:
    query: |
      ```dataview
      TASK
      WHERE !completed AND due = date(today)
      SORT due ASC
      ```
      
  recent_meetings:
    query: |
      ```dataview
      TABLE date, attendees
      FROM "Meetings"
      WHERE date >= date(today) - dur(7 days)
      SORT date DESC
      LIMIT 10
      ```
      
  project_dashboard:
    query: |
      ```dataview
      TABLE status, due, priority
      FROM #project
      WHERE status != "completed"
      SORT priority ASC
      ```

Templates

templates:
  zettelkasten:
    filename: "{{date:YYYYMMDDHHmmss}}"
    content: |
      ---
      id: {{date:YYYYMMDDHHmmss}}
      tags: 
      links: 
      ---
      
      # {{title}}
      
      ## Idea
      
      ## Source
      
      ## Connections
      - Related to: 
      
      ## References
      
  book_note:
    filename: "Book - {{title}}"
    content: |
      ---
      author: {{author}}
      finished: 
      rating: 
      tags: book
      ---
      
      # {{title}}
      by {{author}}
      
      ## Summary
      
      ## Key Ideas
      
      ## Highlights
      
      ## My Thoughts
      
      ## Action Items

Workflow Automations

Web Clipper

web_clipper:
  trigger: browser_extension
  actions:
    - extract_content:
        title: "{{page.title}}"
        url: "{{page.url}}"
        content: "{{selection}}"
    - create_note:
        folder: "Clippings"
        template: web_clip
    - add_tags: ["web-clip", "{{domain}}"]

Research Workflow

research_workflow:
  steps:
    - create_topic_note:
        filename: "Research - {{topic}}"
        folder: "Research"
    - gather_sources:
        search: "{{topic}}"
        link_to_note: true
    - generate_questions:
        based_on: sources
    - create_sub_notes:
        for_each: key_concept

Graph Analysis

graph_insights:
  orphan_notes:
    query: "notes without incoming links"
    action: suggest_connections
    
  clusters:
    identify: true
    visualize: true
    
  link_suggestions:
    based_on: content_similarity
    threshold: 0.7

Best Practices

  1. Atomic Notes: One idea per note
  2. Consistent Naming: Use conventions
  3. Link Liberally: Connect related ideas
  4. Daily Practice: Regular review
  5. Templates: Standardize note types
  6. Tags vs Links: Use both strategically

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.