growth-loops
Skill2 starsChanged 3 months agoMITView on GitHub
Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms, building product-led traction, or understanding how growth loops work.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 71
Create specific loop implementation:
- Distinctive: line 87
Start with the most natural loop for your product
- Distinctive: line 93
Use $ARGUMENTS to pass:
- Distinctive: line 113
Start with one loop and master it before adding complexity
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Growth Loops
Overview
Identify and design growth loops (flywheels) that create sustainable traction. This skill evaluates five proven growth loop mechanisms to reduce reliance on paid acquisition and build product-led growth.
When to Use
- Designing growth mechanisms for a product
- Building sustainable viral or referral traction
- Reducing reliance on paid acquisition
- Analyzing competitor growth strategies
- Optimizing product for product-led growth
The 5 Growth Loop Types
1. Viral Loop
Product content created by users gets shared on external platforms, bringing new users back to the product.
- Mechanism: Users create content in-product → Share on social/external platforms → New users discover and signup
- Example: Figma designs shared as links, Loom videos shared in emails
- Strength: Exponential user acquisition if content is inherently shareable
- Challenge: Requires highly shareable output and strong incentive to share
2. Usage Loop
Users create content or value within the product, then share it, which invites new users or drives re-engagement.
- Mechanism: User creates → Shares creation → Others consume → Become engaged users
- Example: Twitter threads, Medium articles, Notion templates shared publicly
- Strength: Growth tied directly to product usage and network effects
- Challenge: Requires content creation friction to be very low
3. Collaboration Loop
Users invite colleagues to co-create or collaborate within the product, expanding the user base within organizations.
- Mechanism: User creates → Invites colleagues for collaboration → Colleagues discover product value
- Example: Google Docs invitations, Figma team projects, Slack channels
- Strength: Deep organizational penetration and high retention
- Challenge: Works best for collaborative/team-based products
4. User-Generated Loop
Users discover new content or features through other users' creations, then create and share their own content.
- Mechanism: User discovers content → Creates similar content → Shares creation → Others discover
- Example: TikTok, Pinterest, YouTube trends driving creator participation
- Strength: Creates content flywheel and network effects
- Challenge: Requires critical mass of quality content to sustain
5. Referral Loop
Users invite other potential users in exchange for rewards, incentives, or social recognition.
- Mechanism: User refers → Referred user joins → Referrer gets reward → Shares more referrals
- Example: Dropbox referral bonus, Uber rider referrals, PayPal signup bonuses
- Strength: Directly incentivizes acquisition; easy to measure ROI
- Challenge: Requires valuable incentive without eroding unit economics
How It Works
Step 1: Define Product Value
Clarify the core value users experience:
- Primary action users take in your product
- Value created per user action
- Network effects present (if any)
- Friction points in the experience
Step 2: Evaluate Loop Fit
Assess which growth loops align with your product:
- Product type (collaborative, content-based, utility, etc.)
- Target user behavior and sharing habits
- Network effects already present
- Existing user base and engagement
Step 3: Design Loop Mechanics
Create specific loop implementation:
- Trigger that initiates sharing or invitations
- Incentive for participation (intrinsic or extrinsic)
- Ease of sharing mechanism
- Conversion rate from invite to activation
- Frequency of loop repetition per user
Step 4: Calculate Loop Coefficient
Estimate growth velocity:
- Invites/shares per user per cycle
- Conversion rate of invites to new users
- Net new users per cycle
- Time per cycle iteration
Step 5: Build the Loop
Implement the highest-leverage loop first:
- Start with the most natural loop for your product
- Optimize messaging and friction
- Measure loop metrics and conversion rates
- Compound results over time
Input Format
Use $ARGUMENTS to pass:
- Product description and primary user action
- Target user demographics and behavior
- Existing sharing/collaboration features
- Current growth channels and metrics
- Constraints or opportunities
Output
A growth loops analysis including:
- Ranked evaluation of all 5 loop types for your product
- Recommended primary growth loop with implementation plan
- Secondary loops to layer over time
- Key metrics and measurement framework
- 30-60-90 day implementation roadmap
- Potential loop coefficient and growth projections
Framework
Based on growth loops research by Ognjen Bošković. Focuses on compounding user acquisition through built-in, product-native sharing and collaboration mechanisms.
Tips
- Start with one loop and master it before adding complexity
- Viral loops compound fastest but take time to build
- Collaboration loops create strongest retention and LTV
- Measure loop health weekly during optimization phase
- Combine loops for multiplicative effect once operating at scale
Further Reading
Other versions12 projects use a version of this.
Word for word · 7
- skytiger6724/qwen-skills★ 2100% same
- yuusakuri/agent-skills★ 2100% same
- daviszhen/agent-skills★ 1100% same
- miovrag/claude-skills★ 1100% same
- maeng777/claude-skills★ 0100% same
- stefanomartiradonna/claude-skills★ 0100% same
- vijaysuperpositionist/skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 5
- AIDevGTM/gtm-cofounder★ 331same name
- jshsakura/awesome-opencode-skills★ 30same name
- SkeneTechnologies/plg-skills★ 19same name
- brainbytes-dev/everything-claude-marketing★ 9same name
- risadams/ink-and-agency★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository383 other files it gives its agents.
- 37signals-waySkill
- ab-test-analysisSkill
- advisor-orchestrator-workerSkill
- ai-ml-engineeringSkill
- algorithmic-artSkill
- analyze-feature-requestsSkill
- animation-vocabularySkill
- apple-designSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- improve-animationsSkill
- pick-ui-librarySkill
- prototypeSkill
- review-animationsSkill
- ansoff-matrixSkill
- api-and-interface-designSkill
- api-design-best-practicesSkill
- app-store-changelogSkill
- auth-authorizationSkill
- beachhead-segmentSkill
- blue-ocean-strategySkill
- brainstorm-experiments-existingSkill
- brainstorm-experiments-newSkill
- brainstorm-ideas-existingSkill
- brainstorm-ideas-newSkill
- brainstorm-okrsSkill
- brand-guidelinesSkill
- browser-testing-with-devtoolsSkill
- bug-hunt-swarmSkill
- business-modelSkill
- canvas-designSkill
- ci-cd-and-automationSkill
- claude-apiSkill
- clean-architectureSkill
- clean-codeSkill
- cli-creatorSkill
- code-review-and-qualitySkill
- code-review-skillSkill
- code-simplificationSkill
- cohort-analysisSkill
- cold-start-problemSkill
- commit-archaeologistSkill
- competitive-battlecardSkill
- competitor-analysisSkill
- contagiousSkill
- context-engineeringSkill
- continuous-discoverySkill
- architecture-blueprint-generatorSkill
- azure-architecture-autopilotSkill
- cli-masterySkill
- codeqlSkill
- conventional-commitSkill
- create-implementation-planSkill
- csharp-asyncSkill
- diagnoseSkill
- dotnet-best-practicesSkill
- draw-io-diagram-generatorSkill
- git-commitSkill
- github-actions-efficiencySkill
- java-springbootSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

