goblin.tools

Most productivity software is built by people who are good at productivity. That’s the original sin of the category. Notion, Todoist, ClickUp, Asana — these are systems designed by organized minds for other organized minds, and they all quietly assume the hardest part of a task is tracking it. For a large population of users, tracking was never the problem. The problem is that “clean the kitchen” arrives in the brain as a single, undifferentiated, immovable object, and staring at it in a beautifully typeset checkbox does nothing except add guilt.

goblin.tools starts from the opposite assumption. Built by Skyhook Belgium, a small Belgian outfit, and marketed with the cheerfully unserious tagline “smart tools for the neurospicy,” it is not a productivity system at all. It’s a toolbox — a collection of single-purpose AI utilities, each aimed at one specific executive-function failure mode. There’s no dashboard. No projects. No workspaces to configure before you’re allowed to do anything. You land on a page, you type a sentence, you get help, you leave.

The flagship is Magic ToDo, and it’s the reason the store listing sits at 4.8 stars from 2,958 ratings. Around it orbits a suite of deliberately small helpers: the Formalizer, the Judge, the Estimator, the Compiler, the Chef, and newer arrivals like the Taskmaster, Professor and Consultant.

The business model deserves its own paragraph, because it’s genuinely strange. The website is free and ad-free. The mobile apps cost $2.99, once, and Skyhook is explicit that the money pays for hosting first and compensates the developer with whatever’s left. In a market where “AI-powered task breakdown” is a $9.99/month feature bolted onto a subscription you’ll forget to cancel, this reads less like a pricing strategy and more like a position.

• Magic ToDo (with the spiciness slider): Type a task. Pull the chili-pepper slider. At one pepper you get a sensible four-step outline; at maximum heat, “do the laundry” recursively shatters into fifteen-plus micro-steps granular enough that the first one is something you can physically do without thinking. Every step can itself be exploded further. It’s a smart interface metaphor, arrived at via a chili pepper.
• The Estimator: Feed it an activity, get a time estimate. Aimed squarely at time blindness — the inability to intuit whether something takes ten minutes or two hours, which is why the dishes have been “a quick thing I’ll do later” since Tuesday.
• The Compiler: Dump an unstructured, panicked braindump into a box; receive discrete, actionable tasks. This is the on-ramp to Magic ToDo for anyone whose mental state is closer to static than to a list.
• The Formalizer & The Judge: The Formalizer rewrites text to be more formal, casual, sociable or concise. The Judge reads an incoming message and tells you what emotional tone it’s actually carrying. Together they’re a social-translation layer — the least discussed and arguably most quietly useful pair in the box.
• The Chef: Ingredients in, real recipe out. A small mercy at 7pm when deciding what to cook is the entire barrier to cooking.

The Loop That Works

The strength of Magic ToDo is that it attacks the correct variable. Task paralysis is not a motivation deficit; it’s an initiation deficit. The brain cannot find the entry point, so it bounces off the task entirely. Every conventional to-do app responds to this by making the task more visible — bolder, redder, higher in the list — which is roughly like treating a stutter by shouting.

Magic ToDo instead makes the task smaller until it’s beneath the activation threshold. The spiciness slider is the mechanism, and it’s clever for a reason that has nothing to do with AI: it hands the user control over their own granularity. Nobody knows what step size you need today except you, and that number changes hour to hour depending on medication, sleep, and mood. A static breakdown algorithm would be useless. A slider is honest about the variability. Pull it to four peppers on a bad day, one pepper on a good one. That’s not a gimmick; that’s a genuine insight about the user, encoded into a control.

The recursion matters too. Any step that’s still too big gets its own breakdown. You can drill until you hit something with zero friction — “walk to the bedroom,” “pick up the hamper” — and once you’re moving, momentum does the rest. The tool doesn’t need to carry you through the whole task. It only needs to get you past the first thirty seconds.

The Loop That Doesn’t

Here’s where the critique lands: goblin.tools answers “what should I do?” but not “why can’t I start?”

There is no timer. There is no guided, one-step-at-a-time execution mode. Once your task has exploded into fifteen micro-steps, you’re handed the full list — all fifteen — and asked to just, you know, do them. For a user who was overwhelmed by one line of text ninety seconds ago, presenting fifteen is not obviously the win it looks like. The tool solves decomposition and then abandons the user at execution, which is the second half of the same problem.

Worse: there is no saved history of past breakdowns. Think about that for a moment. This is a tool designed explicitly for people with working-memory deficits, and it forgets everything. You broke down “file taxes” into twelve steps last April. This April, you start from zero. You break down the same recurring chore every single week, paying the same small cognitive tax, and the app that exists specifically to reduce cognitive load contributes nothing to that. The audience most likely to benefit from persistence is the audience least served by its absence. This isn’t a missing “nice-to-have.” It’s a hole in the thesis.

There’s no personalization either — the model doesn’t learn that your four-pepper is someone else’s two, or that you always forget the “gather materials” step. And there’s no calendar or task-manager integration, so the Estimator’s useful time data dies in the browser tab where it was born. It can’t feed your calendar. It can’t tell Todoist anything. Every goblin.tools session is a sealed room.

The Ecosystem Problem

The most frustrating criticism isn’t even Skyhook’s fault. goblin.tools has been swarmed by copycat apps with near-identical names charging monthly subscriptions for a worse version of a free thing, with unclear trial pricing on some of those imposters. When your product is free and your clones aren’t, discoverability becomes an attack surface. That the real app still holds 4.8 stars through this is a reasonable proxy for how much people like it.

The aesthetic is unpretentious to the point of being a statement. Flat colors, chunky buttons, a goblin mascot, that chili pepper. It looks like a hobby project — and that’s load-bearing. A slick, corporate-gray interface would carry an implicit accusation: this is a serious tool for serious people, why aren’t you keeping up? The goofiness lowers the stakes. Failing at a goblin’s to-do list is not a moral event.

Four screenshots on the store listing, and honestly that’s all it needs, because there’s not much to show — the app is one text field and a slider. As a design, it’s light on hardware by nature; the real wait is the AI inference between hitting the button and getting your steps, which is inherent to the architecture rather than a flaw. It’s not instant, and that delay lands at exactly the wrong moment psychologically, but nothing here is heavy.

The web version is the canonical experience and remains completely free, which makes the $2.99 apps an act of patronage dressed as a purchase — you’re buying convenience and funding the servers.

On iOS, the share-sheet reachability matters more than you’d think: capturing a task at the instant of realizing it is half the battle. The slider is a good touch control — it wants a thumb, not a mouse. On Android, the experience is functionally identical, though it carries the faint air of a port rather than a co-equal citizen. Neither platform gets widgets, notifications that nudge, or a lock-screen presence — all the ambient hooks that would turn this from a tool you visit into a tool that reaches you. For an audience defined by out-of-sight-out-of-mind, that’s a missed opportunity on both stores.

goblin.tools is a rare piece of software that understands its user better than it understands software. It has no history, no sync, no integrations, no personalization — a feature list that would be disqualifying almost anywhere else. And it still out-thinks the polished, venture-backed productivity suites at the one thing that actually determines whether a task gets done, because Skyhook asked the right question first and built the answer second.

The criticisms are real and they’re structural. Persistence isn’t a roadmap item; it’s the difference between a tool that helps you today and a tool that compounds. A guided execution mode would close the loop the spiciness slider opens. Until those land, goblin.tools remains a strong first act in search of a second.

But at $2.99 — or nothing at all, in your browser — the value proposition isn’t close. We recommend the app to its audience. Not because you need the app; the website works fine. Buy it because someone in Belgium built the thing the entire productivity industry should have built a decade ago, and then declined to rent it to you.