Growth Embedded logo

Growth Embedded

Community
menkesu
growth-embedded

Builds growth loops into products from day 1 using YC playbook (Gustaf Alstromer), Casey Winters growth frameworks, and Elena Verna's retention-first approach. Use when adding viral mechanics, instrumenting analytics, creating referral systems, or optimizing for retention over acquisition.

Overview

Publishermenkesu
Repositoryawesome-pm-skills
Skill namegrowth-embedded
Stars
406
Forks
120
Bundled files
Instructions only
Links
  • 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 menkesu on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/menkesu/awesome-pm-skills.git /tmp/awesome-pm-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-pm-skills/growth-embedded .claude/skills/growth-embedded
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Growth Embedded 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 Growth Embedded 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 Growth Embedded 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.

Growth-First Development

When This Skill Activates

Claude uses this skill when:

  • Building features that could have viral mechanics
  • Adding referral or sharing functionality
  • Implementing analytics and tracking
  • Designing for network effects
  • Optimizing for activation and retention

Core Frameworks

1. YC Growth Playbook (Source: Gustaf Alstromer, Partner at YC)

The Three Growth Levers:

📈 Acquisition - How users discover you 🎯 Activation - First value experience 🔁 Retention - Users coming back

Priority Order:

"Retention first, activation second, acquisition last. Don't acquire users you can't retain."

Growth Loops:

User gets value → Shares with others → New users → Cycle repeats

Examples:

  • Dropbox: More storage for referrals
  • Superhuman: Invite-only creates FOMO
  • Notion: Shared docs bring collaborators

2. Network Effects Patterns

Types:

Direct Network Effects:

  • More users = more value for all
  • Example: Social networks, marketplaces

Data Network Effects:

  • More usage = smarter product
  • Example: Recommendations, AI features

Platform Network Effects:

  • More developers = more integrations
  • Example: Shopify apps, Zapier

3. Referral Mechanics

Double-Sided Incentive:

Referrer gets: [benefit]
Referred gets: [benefit]
Both win: [shared value]

Tracking:

javascript
// Referral flow
generateReferralLink(user) {
  const link = `app.com/ref/${user.id}`;
  track('referral_link_generated', { userId: user.id });
  return link;
}

// Attribution
onSignup(referralCode) {
  const referrer = getUserByRefCode(referralCode);
  track('referral_signup', { 
    referrer: referrer.id,
    referred: newUser.id 
  });
  giveReward(referrer);
  giveReward(newUser);
}

4. Activation Optimization

Time to Value:

"Get users to 'aha moment' as fast as possible"

Activation Milestones:

  1. Signup complete
  2. Setup complete
  3. First value delivered
  4. Habit formed

Measure:

Activation Rate = (Users who reached value) / (Total signups)

Decision Tree: Growth Feature

NEW FEATURE
├─ Can users share this? ──────YES──→ ADD SHARE FUNCTIONALITY
│  NO ↓
├─ Creates network effects? ───YES──→ OPTIMIZE FOR VIRAL LOOPS
│  NO ↓
├─ First-time experience? ─────YES──→ OPTIMIZE ACTIVATION
│  NO ↓
├─ Repeat usage? ──────────────YES──→ INSTRUMENT RETENTION TRACKING
│  NO ↓
└─ STANDARD FEATURE ←──────────────────┘
   (Still track basic analytics)

Action Templates

Template 1: Referral System

markdown
# Referral Feature

## Incentive Structure
- **Referrer gets:** [reward]
- **Referred gets:** [reward]
- **Both benefit:** [shared value]

## Implementation
```javascript
// Generate referral link
const link = generateReferralLink(user);

// Track shares
track('referral_shared', { 
  channel: ['email', 'social', 'link'],
  userId: user.id 
});

// Track conversions
track('referral_converted', {
  referrerId: referrer.id,
  referredId: newUser.id,
  timeToConversion: timestamp
});

// Reward both
giveReward(referrer, 'storage_upgrade');
giveReward(newUser, 'welcome_bonus');

Metrics

  • Link generation rate
  • Share rate
  • Conversion rate (clicked → signed up)
  • Activation rate (signed up → activated)
  • K-factor (viral coefficient)

### Template 2: Activation Flow

```markdown
# Activation Optimization

## Time to Value
- Target: <[X] minutes
- Current: [Y] minutes

## Activation Funnel
1. **Signup** (100% of signups)
2. **Profile Setup** ([X]%)
3. **First Action** ([X]%)
4. **Aha Moment** ([X]%)
5. **Habit Formation** ([X]%)

## Drop-off Points
- Biggest drop-off: [identify]
- Why: [hypothesis]
- Fix: [solution]

## Implementation
```javascript
// Track activation milestones
track('activation_milestone', {
  milestone: 'profile_complete',
  userId: user.id,
  timeToComplete: seconds
});

// Identify where users drop off
if (!completedSetup(user, 24hours)) {
  sendReminderEmail(user);
}

### Template 3: Growth Analytics

```markdown
# Growth Metrics Dashboard

## Acquisition
- New signups: [X per day]
- Channels: [organic, referral, paid]
- Cost per acquisition: [$X]

## Activation
- Activation rate: [X]%
- Time to first value: [X] minutes
- Drop-off point: [step in funnel]

## Retention
- Day 1: [X]%
- Day 7: [X]%
- Day 30: [X]%
- Retention curve: [improving / flat / declining]

## Referral
- K-factor: [X] (viral coefficient)
- Referral rate: [X]% of users refer
- Conversion rate: [X]% of referred sign up

## Implementation
```javascript
// Track key events
track('user_activated', { userId, timestamp });
track('user_retained_day7', { userId, timestamp });
track('referral_sent', { referrerId, channel });

## Quick Reference

### 🚀 Growth Checklist

**Acquisition:**
- [ ] Referral system implemented
- [ ] Viral loops identified
- [ ] Share buttons prominent

**Activation:**
- [ ] Time to value < 5 minutes
- [ ] Onboarding optimized
- [ ] Aha moment clear

**Retention:**
- [ ] Usage triggers implemented
- [ ] Email/push notifications
- [ ] Habit formation designed

**Analytics:**
- [ ] Cohort retention tracking
- [ ] Funnel analysis
- [ ] Attribution tracking

---

## Real-World Examples

### Example 1: Dropbox Referral

**Incentive:**
- Referrer: +500MB storage
- Referred: +500MB storage
- Both win: More space

**Result:** 35% of signups from referrals

---

### Example 2: Superhuman Activation

**Time to Value:**
- < 2 minutes to first email sent
- Guided onboarding
- Keyboard shortcuts taught early

**Result:** 90%+ retention

---

### Example 3: Notion Network Effects

**Growth Loop:**
- User creates doc → Shares with team → Team joins Notion → Creates more docs → Cycle repeats

**Result:** Viral growth in teams

---

## Common Pitfalls

### ❌ Mistake 1: Optimizing Acquisition Before Retention
**Problem:** Leaky bucket - users leave as fast as they join
**Fix:** Fix retention first, then acquire

### ❌ Mistake 2: No Viral Mechanics
**Problem:** Every user requires paid acquisition
**Fix:** Build sharing into core features

### ❌ Mistake 3: Slow Activation
**Problem:** Users drop off before seeing value
**Fix:** Get to aha moment in < 5 minutes

---

## Related Skills

- **zero-to-launch** - For building growth into MVP
- **metrics-frameworks** - For measuring growth metrics
- **exp-driven-dev** - For A/B testing growth features
- **user-feedback-system** - For improving retention

---

## Key Quotes

**Gustaf Alstromer:**
> "Retention first, activation second, acquisition last. Don't pour water into a leaky bucket."

**Casey Winters:**
> "The best growth loops are built into the product, not bolted on."

**Elena Verna:**
> "Acquisition is a tax on poor retention."

---

## Further Learning

- **references/yc-growth-playbook.md** - Complete YC growth frameworks
- **references/referral-examples.md** - Successful referral programs
- **references/activation-patterns.md** - Onboarding best practices
- **references/retention-strategies.md** - Building habit-forming products

Frequently asked questions

What does the Growth Embedded AI skill do?

Builds growth loops into products from day 1 using YC playbook (Gustaf Alstromer), Casey Winters growth frameworks, and Elena Verna's retention-first approach. Use when adding viral mechanics, instrumenting analytics, creating referral systems, or optimizing for retention over acquisition.

Why use Growth Embedded on TypingMind?

Because you install it once and use it with any model. Growth Embedded 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 Growth Embedded in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/menkesu/awesome-pm-skills/tree/main/growth-embedded. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Growth Embedded?

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 Growth Embedded?

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

Is the Growth Embedded AI skill free?

It is published on GitHub by menkesu. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇