Notes Automation Workflows logo

Notes Automation Workflows

Community
AtlasOmnia
notes-automation-workflows

notes-automation-workflows — Automate bulk Apple Notes workflows: discovery, filtering, and scripted enrichment for links/photos.

Overview

PublisherAtlasOmnia
Repositorydonna-starter
Skill namenotes-automation-workflows
Stars
131
Forks
9
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 AtlasOmnia on GitHub. Read the source before you install it.

Installation

Install the Notes Automation Workflows 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/AtlasOmnia/donna-starter/tree/main/skills/notes-automation-workflows
  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/AtlasOmnia/donna-starter.git /tmp/donna-starter
mkdir -p .claude/skills
cp -r /tmp/donna-starter/skills/notes-automation-workflows .claude/skills/notes-automation-workflows
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Notes Automation Workflows 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 Notes Automation Workflows 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 Notes Automation Workflows 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.

Notes Automation Workflows

Use this skill for scripted, repeatable Apple Notes operations that go beyond single-note edits.

When to use

  • "Review my notes from last N days" or periodic cleanup/triage tasks.
  • Adding structured summaries to notes that contain links.
  • Adding summaries for image/photo notes.
  • Updating notes programmatically without manual, one-by-one edits.
  • Creating a translated or otherwise transformed copy of a rich-text note while preserving its structure.

When not to use

  • Single small edits: use the memo/Notes interactive flow directly.
  • Sensitive credential text cleanup: use explicit user confirmation before summarizing.
  • Non-Apple notes sources (Obsidian, Notion, etc.)

Prerequisites

  • macOS Notes.app
  • osascript available
  • User has granted Automation access to Notes.app in System Settings → Privacy & Security → Automation
  • Apple Notes has the target notes in a reachable account (usually iCloud)

memo CLI reliability

The memo CLI tool frequently breaks after Homebrew/Python updates due to a stale interpreter path. Diagnose with /opt/homebrew/bin/memo 2>&1 — typical error: bad interpreter: No such file or directory. Fix via brew uninstall memo && brew install antoniorodr/memo/memo. When broken, fall through entirely to AppleScript (see search section below).

Searching notes reliably

Title-only AppleScript query is the fastest, most reliable search method. Use before any other approach:

bash
# Search by title only — instant even with thousands of notes
osascript -e 'tell application "Notes" to get name of every note whose name contains "keyword"'

# Retrieve title + body of a single matched note (use sparingly)
osascript -e 'tell application "Notes" to set target to first note whose name contains "keyword"' \
 -e '{name:name of target, body:(body of target)}'

Critical timing constraint: Body access (body of n) iterated across every note in a large account times out at 30s. Title-only search has no this problem. Restrict full-body iteration to single-note retrieval or folder-scoped queries.

Core strategy

For anything beyond one note, use AppleScript first-pass enumeration + AppleScript updates. Avoid relying on memo index-based addressing for scripts.

For a single note that must be created and shown on screen, follow the quick-create procedure. It covers the memo bad-interpreter fallback, account/folder discovery, HTML-body creation, show/activate, and folder-scoped read-back verification.

Reliable read/write path

Use AppleScript with body (not plain text) and id:

applescript
tell application "Notes"
 set target to first note whose id is "<note-id>"
 set noteBody to (body of target) as string
 set noteAttachments to count of attachments of target
end tell

Prefer updating by id for correctness and stability.

14-day sweep pattern

When a user asks for the last X days, start with a filtered enumeration in AppleScript so every candidate is in-bounds before heavy processing.

applescript
tell application "Notes"
 set cutoff to (current date) - (14 * days)
 set out to ""
 repeat with a in accounts
 set nset to (notes of a whose (modification date >= cutoff))
 repeat with n in nset
 set out to out & (id of n as string) & "\u001f" & (name of n as string) & "\u001f" & (count of attachments of n as string) & "\u001f" & ((body of n) as string) & "\n"
 end repeat
 end repeat
 return out
end tell

This keeps pagination/sort order issues out of the script and gives a stable candidate list.

Classification rules used in enrichment workflows

After loading candidates, classify each note before writing:

  1. Link note
  • URL regex appears in title or body (http:// or https://).
  1. Photo/attachment note
  • attachments > 0
  • stripped text body is minimal/noisy (len(text) <= ~40) or only boilerplate.
  1. Regular text note
  • No actionable link
  • Non-empty readable text and no dedicated attachment-only signals

For link notes, summarize source content and prepend the note body with a single summary block. For photo-only notes, prepend a concise photo summary block (or a clear placeholder if the image is inaccessible).

Idempotent updates

Never duplicate summary blocks. Before writing, check if body already contains your summary marker, e.g.:

applescript
if (body of target) does not contain "<b>Summary:</b>" then
 set body of target to ("<div><b>Summary:</b> ...</div><div><br></div>") & (body of target)
end if

Content formatting requirements

  • Keep all appended summaries as HTML and prepend via body.
  • Wrap each inserted piece in <div> and separate entries with <div><br></div>.
  • Keep summaries short and task-scoped (2–5 sentences max).

Link-source handling

web_extract coverage varies by site. If a source is unsupported:

  • record that as a blocker in the summary
  • summarize from cached context only when allowed
  • keep a clear label so the next pass can retry when source access improves

Validation checklist

After writes, verify:

  • expected notes in scope were touched
  • link notes now include one summary block each
  • photo/attachment-only notes are marked in a consistent format
  • non-link/non-photo notes were not unexpectedly rewritten

Frequently asked questions

What does the Notes Automation Workflows AI skill do?

notes-automation-workflows — Automate bulk Apple Notes workflows: discovery, filtering, and scripted enrichment for links/photos.

Why use Notes Automation Workflows on TypingMind?

Because you install it once and use it with any model. Notes Automation Workflows 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 Notes Automation Workflows in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AtlasOmnia/donna-starter/tree/main/skills/notes-automation-workflows. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Notes Automation Workflows?

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 Notes Automation Workflows?

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

Is the Notes Automation Workflows AI skill free?

Yes. It is published on GitHub by AtlasOmnia 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 👇