Official skill · Product
Habit loop review
Reviews repeat use with the Hooked Model (trigger, action, variable reward, investment), finds the weakest phase from usage data, and checks the habit serves the user. Use it when users try the product and don't come back.
AI skill
Have your AI find why users don't come back, and what to fix first
14 days free · No card needed
Works in Claude, ChatGPT, and coding agents. On Team and Business, the official skill in your pod updates itself when we improve it.
When to use it
- Users try the product and don't come back
- Deciding what to change first for weekly or daily use
- Before adding notifications, streaks or rewards
What you give it
- What the product does and how often it should be used
- Return rates and repeat actions
- Current triggers
- What users store in it
What you get
The loop by phase with evidence, the weakest phase with one change and a metric, other changes, and an ethics check.
How it works
- Set the habit target
- Name the internal trigger
- Review the external triggers
- Review the action
- Review the reward
- Review the investment
- Pick the weakest phase
- Run the ethics check
Example
What you give it
Our app helps restaurant managers in Bogotá order produce from local suppliers. Managers should order 3 times a week. Data: 61% of new managers place a first order; only 18% order in week 4. Repeat managers almost all use 'reorder last basket'. The only trigger is a weekly promo email. Ordering takes 9 taps. Prices change daily and managers say they open the app 'to see if tomatoes went down'. Nothing is saved except the last basket.
What you get back (the start of it)
Habit loop review: produce ordering app
Habit target: a restaurant manager places an order 3 times a week.
The loop today
| Phase | What happens now | Evidence | Strength |
|---|---|---|---|
| Internal trigger | Not knowing today's prices before ordering | managers open the app "to see if tomatoes went down" | ok |
| External trigger | Weekly promo email | the only trigger; doesn't match a 3-a-week rhythm | weak |
| Action | 9 taps to order; "reorder last basket" is shorter | repeat managers almost all reorder | ok |
| Variable reward | Daily prices: today's tomatoes may be cheaper | managers check for price drops | strong |
| Investment | Only the last basket is saved | nothing else is stored | weak |
Weakest phase
External trigger — 61% order once but 18% order in week 4, and the only prompt is weekly and promotional. Change: a message on each manager's usual order days with today's prices for their last basket, linking straight to reorder. · Metric: week-4 ordering rate.
The rest of this output, the full steps and the checks the AI runs before it answers are in your pod once you add the skill.
Use this skill in your AIShare it with your team
Add it to an AI Skill Pod and everyone on the team, contractors included, uses the same version from their own AI. Read the best ways to share AI skills with a team
Changelog
- v1.0.0 · · First release.
Sources
- Nir Eyal: The Hooked Model (read 2026-11-04)
- Wikipedia: Nir Eyal (read 2026-11-04)