Daily Note Wrapup logo

Daily Note Wrapup

Community
AtlasOmnia
daily-note-wrapup

daily-note-wrapup — Create, verify, and index daily wrap-up notes in an Obsidian vault.

Overview

PublisherAtlasOmnia
Repositorydonna-starter
Skill namedaily-note-wrapup
Stars
131
Forks
9
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Daily Note Wrapup 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/note-taking/daily-note-wrapup
  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/note-taking/daily-note-wrapup .claude/skills/daily-note-wrapup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Daily Note Wrapup 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 Daily Note Wrapup 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 Daily Note Wrapup 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.

Daily Note Wrap-Up Workflow

Use this skill for evening wrap-up work that creates tomorrow's daily note and updates the monthly daily-note index.

Core rules

  • Treat the requested daily-note structure as a contract; preserve section order exactly.
  • Carry forward incomplete work into tomorrow's note.
  • On weekends, omit any work-specific section (for example ### [Work]) entirely rather than leaving an empty heading or placeholder bullet.
  • If a section has nothing to place, follow the user's exact omission rule for that section rather than inventing filler text.
  • Keep today's note untouched; only create or update tomorrow's note and the monthly index.
  • Serialize all mutations to the same file. Never launch parallel patches against one note or monthly index; combine related edits into one cohesive patch when practical, or patch sequentially with a read-back between changes.

Structure gotchas

  • The daily note template is not a generic form: match the user's requested headings and ordering exactly, including weekend-only omissions.
  • Do not leave a blank ### [Work] heading on weekends; remove the section entirely.
  • Use None only where the requested structure explicitly asks for it (for example, Waiting / Blocked), and omit empty sections otherwise.

Recommended workflow

  1. Determine today's date and tomorrow's date in the relevant timezone.
  2. Read today's daily note and extract useful context from ## Log and ## Wins.
  3. Gather carry-forward items from incomplete work and overdue Todoist items. Treat these as independent inputs: unchecked items in today's note still carry forward even when Todoist returns no matches. Before interpreting an empty Todoist result as "nothing due," confirm that the command actually applied date/filter semantics rather than literal keyword matching; preserve the command evidence, but do not silently discard known pending work.
  4. Write tomorrow's daily note with the exact requested structure.
  5. Update the monthly index for the target month under the correct ## Weekdays or ## Weekends section.
  6. Read both files back from disk before reporting completion.
  7. If the on-disk note looks stale, reordered, or partially replaced, rewrite the whole file through a sibling temp file + atomic rename and then re-read before trusting the result.
  8. If the atomic replacement still snaps back after a delay, stage the intended note, then run scripts/atomic-note-replace-verify.sh <intended-note> <target-note>. It atomically replaces the target, protects the new inode while a stale one-shot writer abandons its write, clears protection safely, and proves byte stability for 30 seconds locked plus 20 seconds unlocked. Afterward, separately validate the note's required headings/content and the monthly index.

Verification

  • If there is no canonical test or build command, create a temporary verification script under tempfile.gettempdir() with a hermes-verify- filename prefix.
  • Run the script against the on-disk note contents, then remove it when finished.
  • Report this as ad-hoc verification, not a green test suite.
  • After writing, verify the actual file on disk, not just the write tool response. If a note read-back looks stale or mismatched, do not trust the snapshot; confirm with a direct filesystem read (Path.read_text() / stat()) and, if needed, perform an atomic temp-file rewrite before declaring success.

Monthly index cleanup

  • Add the target day's wikilink under the correct weekday/weekend section.
  • If a placeholder or draft link exists for the same date, replace it with the canonical wikilink.
  • Do not leave duplicate entries for the same day.

Pitfalls

  • Whole-note rewrites are often safer than fragile incremental edits when the target structure must be exact.
  • A note that looks correct in a write response still needs a filesystem read-back.
  • Treat a concurrent-modification warning followed by an immediate read-back of the old template scaffolding as evidence of an active stale writer. Do not retry another ordinary live-file rewrite; move directly to the sibling-temp atomic replacement and bounded immutable-hold procedure (see the script and the notes above).
  • Verify the daily note and monthly index independently: a stale writer may revert the note while the index update remains correct.
  • If another process may be touching the note, verify the final on-disk text rather than trusting an intermediate snapshot.

Support files

  • scripts/atomic-note-replace-verify.sh — reusable macOS atomic replacement with cleanup traps and 30-second locked plus 20-second unlocked SHA-256 stability checks.

Public support files

  • scripts/atomic-note-replace-verify.sh

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Daily Note Wrapup AI skill do?

daily-note-wrapup — Create, verify, and index daily wrap-up notes in an Obsidian vault.

Why use Daily Note Wrapup on TypingMind?

Because you install it once and use it with any model. Daily Note Wrapup 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 Daily Note Wrapup in TypingMind?

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

Which AI models can use Daily Note Wrapup?

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 Daily Note Wrapup?

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

Is the Daily Note Wrapup 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 👇