skills-ws/skills/product-led-growth/references/3-viral-loops-network-effects.md

87 agent skills for AI coding assistants — marketing, growth, web3, dev, design & operations. Built for OpenClaw, Claude Code, Cursor, and Codex.

## Contents

- 3. Viral Loops & Network Effects
- Types of Viral Loops
- Viral Coefficient (K-Factor)
- Designing Invite Flows That Don't Feel Spammy
- Collaboration-Driven Virality

## 3. Viral Loops & Network Effects

### Types of Viral Loops

**1. Inherent virality (strongest)**
Product REQUIRES others to get value. Can't use it alone effectively.
- Slack: messaging needs recipients
- Zoom: meetings need participants
- Figma: design review needs collaborators
- Google Docs: sharing IS the product

**2. Artificial virality (referral programs)**
Incentivized sharing. User gets reward for inviting others. (Reward amounts below are illustrative — programs and payouts change; verify current terms before quoting.)
- Dropbox: bonus storage per referral, double-sided (the canonical example)
- Uber: ride credit for both referrer and referee
- Notion: account credit per successful referral
- Robinhood: free stock for both parties (subject to eligibility)

Double-sided rewards (both parties benefit) consistently outperform one-sided ones — they give the sender a non-awkward reason to invite.

**3. Content virality (organic distribution)**
User-created content gets shared outside the product.
- Canva: designs shared on social with "Made with Canva" watermark
- Spotify Wrapped: annual recap goes viral on social
- Loom: video links shared in emails/Slack expose brand
- Calendly: scheduling links expose product to every invitee

### Viral Coefficient (K-Factor)

```
K = i × c

Where:
i = average invitations sent per user
c = conversion rate of invitations (% who sign up)

K > 1.0 = exponential growth (each user brings > 1 new user)
K = 0.5-1.0 = amplified growth (good — each user brings half a new user)
K < 0.5 = weak virality (supplement with paid/organic acquisition)
```

**Example:**
- Average user invites 5 people → i = 5
- 15% of invitees sign up → c = 0.15
- K = 5 × 0.15 = 0.75
- Each user brings 0.75 new users → growth amplified but not exponential

**Viral cycle time matters too:**
```
Effective growth = K / cycle_time
```
K=0.5 with 1-day cycle > K=0.8 with 30-day cycle.

### Designing Invite Flows That Don't Feel Spammy

**Principles:**
- Invite should provide value to the RECIPIENT, not just the sender
- Trigger invites at moments of delight (just completed something, got results)
- Never auto-send without explicit user action
- Let user customize the invite message
- Show who's already on the platform from their contacts (social proof)

**Invite flow best practices:**
1. Contextual trigger: "Share this project with your team" (not random popup)
2. Easy mechanics: email, link, or direct integration (Slack, Teams)
3. Recipient experience: personalized landing page, skip straight to value
4. Double-sided incentive: both parties benefit
5. Follow-up: one reminder max, then stop

### Collaboration-Driven Virality

The most sustainable viral loop — product gets better with more users:
- **Slack**: more teammates = more useful channels
- **Miro**: more collaborators = richer boards
- **GitHub**: more contributors = better code
- **Figma**: designer invites developers for handoff → developers invite PMs for review

**Design for collaboration:**
- Make sharing a core workflow (not a bolt-on)
- Show value of collaboration ("3 teammates are viewing this")
- Enable different roles (viewer, editor, admin) to lower invite friction
- Cross-functional sharing (designer → developer → PM chain)