Things Todo

CommunityPopular

steipete

things-todo

Things 3 via things CLI: add, list, search, update, delete, verify.

Overview

Publisher	steipete
Repository	`agent-scripts`
Skill name	`things-todo`
Stars	6.6K
Forks	547
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 steipete on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/steipete/agent-scripts.git /tmp/agent-scripts
mkdir -p .claude/skills
cp -r /tmp/agent-scripts/skills/things-todo .claude/skills/things-todo

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Things Todo 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 Things Todo 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 Things Todo 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.

Things Todo

Use this for Things 3 tasks on Peter's Macs. Prefer things for Things-backed todos; use $reminders only when the user asks for Apple Reminders.

Tool

CLI: things
Repo: https://github.com/ossianhempel/things3-cli
Install:

bash
GOBIN=/opt/homebrew/bin go install github.com/ossianhempel/things3-cli/cmd/things@latest

Auth for update URL operations:

bash
source ~/.profile >/dev/null 2>&1 || true
things auth

THINGS_AUTH_TOKEN should come from ~/.profile or 1Password. Never print it. things update --dry-run must redact it as auth-token=***.

Start

Use JSON for scripted reads and verification:

bash
things tasks --format json --limit 20
things today --format json
things search "query" --format json

Things DB reads may need Full Disk Access for the calling app. Writes should go through Things URL Scheme or AppleScript via things; do not write the SQLite DB directly.

Add

Default: add, then search/read back.

bash
things add "Book LHR-SFO nonstop business flight" --notes "Nonstop only." --when tomorrow --tags travel
things tasks --search "LHR-SFO" --format json

Useful flags:

--notes "text"
--when today|tomorrow|evening|anytime|someday|YYYY-MM-DD
--deadline YYYY-MM-DD
--list "Project or Area"
--tags tag1,tag2
--checklist-item "text" repeatable
--dry-run to inspect the things:/// URL without mutating.

Update / Delete

Find the UUID first, then mutate by id:

bash
things tasks --search "flight" --format json
things update --id <uuid> "New title" --notes "Updated notes"
things tasks --search "New title" --format json
things delete --id <uuid> --confirm <uuid>
things tasks --search "New title" --format json
things trash --search "New title" --format json

Always read back after writes. Delete moves items to Things Trash; verify normal search is empty and trash search contains the item when cleanup matters.

Conventions

Turn vague asks into concrete next-action titles.
Preserve wording when the user clearly wants capture, not rewriting.
Split unrelated actions into separate to-dos.
Use Today only when the user implies it; otherwise use Inbox/Anytime defaults.
Prefer --dry-run before bulk updates/deletes.
For current date math, run date; do not guess.

Gotchas

macOS only; remote hosts may show Things.app version as UNKNOWN if the app is absent or not visible there.
update needs THINGS_AUTH_TOKEN; add does not.
--tags is plural for add/update; tasks --tag is singular for filtering.
today JSON may show start: Anytime plus a real start_date; use command membership/read-back, not one field alone, to verify Today placement.

Frequently asked questions

What does the Things Todo AI skill do?

Things 3 via things CLI: add, list, search, update, delete, verify.

Why use Things Todo on TypingMind?

Because you install it once and use it with any model. Things Todo 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 Things Todo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/steipete/agent-scripts/tree/main/skills/things-todo. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Things Todo?

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 Things Todo?

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

Is the Things Todo AI skill free?

Yes. It is published on GitHub by steipete 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

Kotlin Testing

affaan-m

CommunityPopular

Patrones de pruebas Kotlin con Kotest, MockK, pruebas de coroutines, pruebas basadas en propiedades y cobertura con Kover. Sigue la metodología TDD con prácticas idiomáticas de Kotlin.

Laravel Patterns

Patrones de arquitectura Laravel, routing/controladores, Eloquent ORM, capas de servicio, colas, eventos, caché y API resources para aplicaciones en producción.

Laravel Security

Buenas prácticas de seguridad en Laravel para autenticación/autorización, validación, CSRF, asignación masiva, subida de archivos, secretos, limitación de velocidad y despliegue seguro.

Laravel Tdd

Desarrollo guiado por pruebas para Laravel con PHPUnit y Pest, factories, pruebas de base de datos, fakes y objetivos de cobertura.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Things Todo

Tool

Start

Add

Update / Delete

Conventions

Gotchas

Frequently asked questions

Related AI Skills

Set up your own AI workspace now