本文へ移動
cccskills
無料GitHub で公開

retention-design

Design retention and engagement features using the Hook Model. Use when the user says "improve retention", "reduce churn", "make it habit-forming", "engagement design", "hook model", "trigger action reward", "users aren't coming back", "increase DAU/MAU", or wants to design features that bring users back repeatedly - even if they don't explicitly say "Hook Model".

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Overview

Based on Hooked by Nir Eyal. The Hook Model is a four-phase loop that drives habit formation in products. Habits require frequent, perceived utility, and a degree of pain when the habit is disrupted. Products that become habits are harder to churn from - not because users are locked in, but because the product genuinely fills a need they return to automatically.

The four phases: Trigger - Action - Variable Reward - Investment

Use this skill ethically. Eyal's own caveat: design habits for products that genuinely improve users' lives. Manipulating users into unhealthy habits is both wrong and unsustainable.

Workflow

Step 1: Define the habit you want to create

What behavior should become automatic?

  • Frequency target: daily / weekly / monthly?
  • Context: when and where does this behavior occur?
  • Current alternative: what do users do today instead?

Step 2: Design the Trigger

Triggers prompt action. Two types:

  • External triggers - notifications, emails, badges, prompts (used early in habit formation)
  • Internal triggers - emotions or situations that cue the behavior automatically ("I feel anxious - I open [app]")

The goal: move users from external to internal triggers over time.

For your feature: what external trigger will prompt first use? What internal trigger will sustain it?

Step 3: Design the Action

Eyal's formula: Motivation + Ability + Trigger = Action

Reduce friction on the action:

  • How many steps to complete the action?
  • What's the minimum viable action? (e.g. one tap, not a form)
  • Where does motivation need to be highest? Remove barriers there.

Fogg's six elements of simplicity: time, money, physical effort, brain cycles, social deviation, non-routine. Reduce the one that's the biggest barrier.

Step 4: Design the Variable Reward

Variable rewards drive repeat behavior (Skinner's research). Three types:

  • Rewards of the tribe - social validation, belonging (likes, comments, leaderboards)
  • Rewards of the hunt - seeking resources or information (feed, search results, deals)
  • Rewards of the self - mastery, completion, consistency (streaks, progress bars, achievements)

Key: variability is what makes rewards compelling. Predictable rewards lose their pull. Design for some uncertainty in the reward.

Step 5: Design the Investment

Investment makes users more likely to return. Four forms:

  • Data - users store value (photos, notes, history)
  • Content - users create things (posts, lists, playlists)
  • Followers - social capital that exists only in your product
  • Reputation/skill - progress that would be lost by leaving

Investment also loads the next trigger: "You have 3 unread notifications" brings users back.

Step 6: Map the full Hook loop

Draw the loop explicitly:

Trigger     -> [what prompts the behavior]
Action      -> [the simplest behavior]
Reward      -> [what the user gets, with some uncertainty]
Investment  -> [what the user puts in that makes them return]
             -> Next Trigger: [how investment loads the next trigger]

Step 7: Ethical check

Before shipping: would you be comfortable if users knew exactly how you designed this? Would you use this product yourself? Would you recommend it to someone you care about?

Anti-Patterns

1. Designing triggers without investment Bad: Sending notifications that bring users in but give them nothing to do. Good: Every trigger should lead to an action that builds investment.

2. Predictable rewards Bad: "You earned 10 points" every single time. Good: Variable - sometimes 10 points, sometimes a badge, sometimes a streak milestone. Variability sustains engagement.

3. Investment that traps instead of enriches Bad: Making it painful to leave (dark patterns, data hostage-taking). Good: Investment that genuinely improves the product for the user over time.

4. External triggers forever Bad: Users still need a push notification to open the app after 6 months. Good: Design toward internal triggers. If users don't develop internal triggers, the habit hasn't formed.

Quality Checklist

  • Habit defined: behavior, frequency, context
  • External trigger designed for acquisition
  • Internal trigger identified for sustained habit
  • Action reduced to minimum friction
  • Variable reward designed (not fixed/predictable)
  • Investment mechanism builds value users would lose by leaving
  • Full Hook loop mapped explicitly
  • Ethical check passed

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

日本語の概要は準備中です。原文の説明を表示しています。

qa-aman/claude-skills202026年9月10日 更新

qa-aman のスキルをすべて見る

このスキルの問題を報告する