duo-retention

スター2

フォーク0

更新日2026年5月4日 16:55

Duolingo-style retention engineering for any product — habit loops, streaks, leagues, churn diagnostics, day-N drop-off, and the discipline of building a "forever product." Use when the user asks how to keep users coming back, debug churn, design a streak system, time push notifications, run a leaderboard, or shift a product's metric from acquisition to retention. Source the Duolingo Handbook (Take the Long View) and blog data posts; translate every pattern to the user's actual product.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

ソース

HKTITAN

HKTITAN/duolingo

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Duolingo Retention — Map of Content

Duolingo's central business bet is that retention compounds and acquisition does not. The handbook frames the company as a "forever product": every decision is judged by long-term retention, not short-term revenue. This skill packages that bet into reusable patterns.

This skill is structured as a graph: scan the descriptions below, follow only the [[wikilinks]] you need. Don't read every node up front.

Foundations

[[references/forever-product]] — the operating premise: optimize for users who stick around for years, not quarters.
[[references/habit-loop]] — trigger → action → variable reward → investment, the spine of every retention move.
[[references/retention-vs-revenue]] — the explicit tradeoff Duolingo makes (and limits) between monetization and long-term return.

Behavioral mechanics

[[references/streak-mechanics]] — the daily-counter habit engine that became the company's icon.
[[references/streak-freeze]] — why protecting the streak is the retention move, not the gentle one.
[[references/loss-aversion]] — the asymmetry that makes streaks work: losing hurts more than winning feels good.
[[references/variable-reward]] — unpredictable payoffs (chests, league finishes) outperform predictable ones.
[[references/friction-as-stickiness]] — small required actions that build identity and habit.

Social and competitive layers

[[references/leagues]] — weekly time-boxed competition with promotion and demotion.
[[references/daily-quests]] — short-horizon goals that set up the long-horizon streak.

Diagnosing and fixing churn

[[references/churn-diagnostics]] — how to find the day where users drop and what each drop-off shape implies.
[[references/notification-discipline]] — the long-term cost of over-notifying, and how Duolingo decides cadence.

Sibling skills

[[../duo-gamification/SKILL]] — the play layer (XP, juicy feedback, hearts) that makes the retention loops survivable.
[[../duo-voice/SKILL]] — the copy layer that makes a push notification fire instead of fizzle.
[[../duo-experimentation/SKILL]] — every retention claim in this skill was originally an A/B test; here's how to run yours.
[[../duo-product/SKILL]] — the "forever product" mental model lives in the product skill too; the long-view bet starts there.

Sources

Duolingo Handbook (2025), Principle #1: Take the Long View
blog.duolingo.com — streak society, league design, push-notification science posts

このリポジトリの他の Skills

同じリポジトリ

duo-culture

HKTITAN/duolingo

Build the team the way Duolingo built theirs — the Green Machine operating model, talent density over headcount, candor protocol ("focus on what, not who"), hire-slow / fire-fast, and the "no process unless it makes decisions better" rule. Use when the user is hiring, defining team rituals, debating remote vs. office, choosing a feedback model, or installing an operating system in a team that has none. Source the Duolingo Handbook (Raise the Bar + Green Machine).

2026-05-042

duo-design

HKTITAN/duolingo

UI patterns from the Duolingo design system — juicy motion, the character system as the emotional channel, design tokens (color/type/spacing), sound as a UX surface, accessibility as a default not a checklist, and "error-as-delight" detailing. Use when the user is designing a screen for a gamified or learning product, reviewing a design for "why does this feel flat," picking a motion system, building a character mascot, or auditing for accessibility. Source the Duolingo design system at design.duolingo.com.

2026-05-042

duo-experimentation

HKTITAN/duolingo

Duolingo-style experimentation as a decision protocol — hundreds of A/B tests a week, opinions resolved by data, ideas killed quickly. Covers hypothesis design, metric selection, guardrails, sample size, novelty effects, and explicit kill criteria. Use when the user wants to run an A/B test, decide between two designs without arguing, set up an experiment program, debug why a test isn't moving, or build a culture where "show don't tell" replaces seniority-based decisions. Source the Duolingo Handbook (Show Don't Tell) and engineering blog posts.

2026-05-042

duo-gamification

HKTITAN/duolingo

Add Duolingo-style play to any product — XP systems, juicy feedback, leagues, celebration moments, hearts/energy, and the anti-grind discipline that keeps gamification from turning toxic. Use when the user asks how to make a product fun, addictive, or "feel like a game," when designing rewards, levels, or progress, or when an existing system feels like a slot machine and they want it to feel like a craft. Source the Duolingo Handbook (Make It Fun) and the Duolingo design system.

2026-05-042

duo-growth

HKTITAN/duolingo

Duolingo-style growth that doesn't break retention — viral loops, brand-as-acquisition (the TikTok playbook), referral mechanics, localization as a growth lever, and the founder-mode marketing that turned a mascot into a meme. Use when the user is planning acquisition, building a referral system, considering paid vs. organic, evaluating a marketing channel, or trying to turn an existing brand into a growth engine. Source the Duolingo Handbook (Make It Fun) and observed marketing patterns from 2022–2025.

2026-05-042

duo-product

HKTITAN/duolingo

Make product decisions the way Duolingo does — long-view over short-term, ruthless prioritization, ship-and-learn over plan-and-ship, dogfooding, and the "intuitive by default" quality bar. Use when the user is roadmapping, deciding what to cut, debating whether to ship, defining a quality bar for a feature, or trying to install a "product-led" culture in a team that defaults to feature factories. Source the Duolingo Handbook principles 1, 2, and 3 (Take the Long View, Raise the Bar, Ship It).

2026-05-042

name	duo-retention
description	Duolingo-style retention engineering for any product — habit loops, streaks, leagues, churn diagnostics, day-N drop-off, and the discipline of building a "forever product." Use when the user asks how to keep users coming back, debug churn, design a streak system, time push notifications, run a leaderboard, or shift a product's metric from acquisition to retention. Source the Duolingo Handbook (Take the Long View) and blog data posts; translate every pattern to the user's actual product.
license	MIT
metadata	{"author":"HKTITAN","version":"1.0.0","graph":true}

Duolingo Retention — Map of Content

This skill is structured as a graph: scan the descriptions below, follow only the [[wikilinks]] you need. Don't read every node up front.

Foundations

[[references/forever-product]] — the operating premise: optimize for users who stick around for years, not quarters.
[[references/habit-loop]] — trigger → action → variable reward → investment, the spine of every retention move.
[[references/retention-vs-revenue]] — the explicit tradeoff Duolingo makes (and limits) between monetization and long-term return.

Behavioral mechanics

[[references/streak-mechanics]] — the daily-counter habit engine that became the company's icon.
[[references/streak-freeze]] — why protecting the streak is the retention move, not the gentle one.
[[references/loss-aversion]] — the asymmetry that makes streaks work: losing hurts more than winning feels good.
[[references/variable-reward]] — unpredictable payoffs (chests, league finishes) outperform predictable ones.
[[references/friction-as-stickiness]] — small required actions that build identity and habit.

Social and competitive layers

[[references/leagues]] — weekly time-boxed competition with promotion and demotion.
[[references/daily-quests]] — short-horizon goals that set up the long-horizon streak.

Diagnosing and fixing churn

[[references/churn-diagnostics]] — how to find the day where users drop and what each drop-off shape implies.
[[references/notification-discipline]] — the long-term cost of over-notifying, and how Duolingo decides cadence.

Sibling skills

[[../duo-gamification/SKILL]] — the play layer (XP, juicy feedback, hearts) that makes the retention loops survivable.
[[../duo-voice/SKILL]] — the copy layer that makes a push notification fire instead of fizzle.
[[../duo-experimentation/SKILL]] — every retention claim in this skill was originally an A/B test; here's how to run yours.
[[../duo-product/SKILL]] — the "forever product" mental model lives in the product skill too; the long-view bet starts there.

Sources

Duolingo Handbook (2025), Principle #1: Take the Long View
blog.duolingo.com — streak society, league design, push-notification science posts