Linear
asgeirtj/system_prompts_leaks
Read and manage software issues, tickets, projects, and planning data in Linear.
Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business.
MITAuto-check passed
Install Growth Model
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RefoundAI/lenny-skills growth-model --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/growth-model .claude/skills/growth-model && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .claude/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-modelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RefoundAI/lenny-skills growth-model --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/growth-model .agents/skills/growth-model && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .agents/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RefoundAI/lenny-skills growth-model --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/growth-model .cursor/skills/growth-model && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .cursor/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/RefoundAI/lenny-skills.git --path skills/growth-model--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RefoundAI/lenny-skills growth-model --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/growth-model .gemini/skills/growth-model && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .gemini/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install RefoundAI/lenny-skills growth-modelInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/growth-model .github/skills/growth-model && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .github/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill growth-model -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RefoundAI/lenny-skills growth-model --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/growth-model .opencode/skills/growth-model && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "growth-model" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/growth-model into .opencode/skills/growth-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "growth-model", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
growth-model- GitHub stars
- 1.4k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 1,158 words
- Files
- 3 (incl. references)
- Skills in repo
- 76
- Repo updated
- First seen
- Licence
- MIT
At a glance
Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business.
- Works in 4 steps: Audit current mechanics - Assist the… → Visualize the model - Guide the user to… → Quantify the loops - Help the user build… → …
- SKILL.md covers How to Help, Core Principles, Templates & Frameworks and Questions to Help Users, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Growth Model is an agent skill from RefoundAI/lenny-skills. Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/artifacts.md` and `references/guest-insights.md`).
The repository describes itself as: 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more. The licence is MIT.
Example prompts
- “/growth-model”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Audit current mechanics - Assist the user in identifying whether their current growth is driven by SEO, paid ads, sales, or virality based…
- Visualize the model - Guide the user to map out their growth as a system of interconnected, reinforcing loops rather than a one-way funnel.
- Quantify the loops - Help the user build a mathematical representation of their growth variables in a spreadsheet to stress-test their…
- Identify constraints - Analyze where growth is stalling by diagnosing failure points in the user journey from acquisition to retention.
What it can do on your machine
Read from SKILL.md and the folder at commit 13598cc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Growth Model loads about 1.9k tokens when it runs, and up to ~62k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 1,158 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from RefoundAI/lenny-skills at commit 13598cc, republished under its MIT licence (© RefoundAI). 1,158 words, ~1,937 tokens.
Download SKILL.mdSave it as
.claude/skills/growth-model/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- growth-model
- description
- Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business.
Building a Sustainable Growth Model
Move beyond linear funnels to build compounding loops that drive scalable, long-term product growth.
Help the user with building a sustainable growth model using insights from 16 guests and posts across Lenny's Podcast and Newsletter.
How to Help
- Audit current mechanics - Assist the user in identifying whether their current growth is driven by SEO, paid ads, sales, or virality based on product characteristics.
- Visualize the model - Guide the user to map out their growth as a system of interconnected, reinforcing loops rather than a one-way funnel.
- Quantify the loops - Help the user build a mathematical representation of their growth variables in a spreadsheet to stress-test their assumptions.
- Identify constraints - Analyze where growth is stalling by diagnosing failure points in the user journey from acquisition to retention.
Core Principles
Loops over funnels
Shishir Mehrotra: "But I highly encourage drawing a diagram like this for your business. I'll flash it up on screen for a second and I'll describe it, but this is what the diagram looks like, black loop, blue loop, and it's basically the two different ways that our product spreads. The Black Loop is someone comes in, they make a doc, they share with a group of people, some subset of the people turn around and make another doc, and the process repeats itself over and over again."
Visualize growth as recurring loops where the output of one cycle becomes the input for the next, creating organic mechanisms for scaling.
Mathematical reconciliation
Dan Hockenmaier: "And that's how I think about a growth model, so the analytical representation of how the business grows and it's typically built in a spreadsheet which has a really nice feature of being very hard to fake. You can talk about a business conceptually, but when you actually have to get it to line up and link in a model, it's very hard to not force yourself to understand how the business works."
Building your model in a spreadsheet forces you to reconcile conceptual theories with mathematical reality, ensuring all variables are linked.
Prioritize volume via low barriers
Archie Abrams: "In a given cohort of merchants, a lot of people will start. Some of those people on their first attempt that's entrepreneurship might not succeed, but the folks who do go on to be successful will make that entire cohort of merchants who started something that makes Shopify as a business extremely successful. And that's why we lower the barriers to get started and help folks grow, and those winners make the whole thing work."
In power law models, maximizing top of funnel volume by lowering entry barriers is more effective for long term revenue than early optimization.
Capture kinetic energy
Sarah Tavel: "This is where I love to think of every time a user users your product, let's say they're clicking on the mouse or they're tapping on their phone, I love to think of it as this kinetic energy that they're putting into your product. You're taking that energy, and your job with a great product, is to take that energy and, as much as possible, convert it back to the experience that they're having with your product."
Sustainable growth is achieved by converting individual user actions into collective network effects that improve the product for everyone.
Target high density networks
Nikita Bier: "We found that as a user got older from age 13 to 18, the number of people that they invite to an app just declines almost exponentially. Finally, and the most important thing is they see each other every day, and that is so critical."
Viral growth is exponentially easier in demographics with high daily physical proximity and malleable social habits, such as younger cohorts.
Layer motions strategically
Elena Verna 3.0: "Wait for growth until you are ready to overlay product-led growth on top of your sales motion. ... honestly, the longer you wait, the better it is because that way your entire company will be trained to be responsible for growth."
Avoid siloing growth; instead, layer different motions like product-led growth only after your primary sales or marketing motion is stable.
Show full SKILL.md (468 more words)Show less
Templates & Frameworks
- Magical Growth Loops Taxonomy (Magical growth loops) - A 4-type classification of growth loops where existing users recruit new users, each with active and passive sub-types. Used to brainstorm and identify latent g
- The Racecar Growth Framework (60 ideas to boost your growth) - A framework co-authored by Lenny and Dan Hockenmaier that maps business growth to four components of a high-performance race car, helping teams categorize and p
- Growth Model Framework (Growth Levers × Growth Motions) (Six rules of hiring for growth) - A framework for defining your company's growth model by combining growth levers (acquisition, retention, monetization) with growth motions (product-led, sales-l
- ARIA Framework (How to accelerate growth by focusing on the features you already have) - A four-principle framework for increasing engagement with existing features to drive product growth. Designed to be used as an ongoing, repeatable process (not
- 30+ Company Growth Loop Examples (Magical growth loops) - Comprehensive catalog of real companies and their specific magical growth loops, organized by loop type
- Growth Loop Brainstorming Questions (Magical growth loops) - Derived from the taxonomy — a set of questions to evaluate whether your product has a latent magical growth loop
- Duolingo User Engagement Bucket Model (MECE Growth Model) (How Duolingo reignited user growth) - A closed-circuit user segmentation model where every user who has ever used the product is in exactly one bucket on any given day, with arrows representing dail
See references/artifacts.md for the full list with details.
Questions to Help Users
- "What is the single core action a user takes that naturally leads to another user joining or an existing user returning?"
- "If you stopped all paid marketing tomorrow, which organic loops would continue to generate new users?"
- "Is your business model's primary advantage found in its margins, its search authority, or its viral coefficient?"
- "Can an end-user discover, use, and upgrade your product without any human intervention from your team?"
- "Which user cohort has the highest 'kinetic energy' and how are you converting that into product value for others?"
- "Does your current growth model rely on a 'magic wand' hack or a repeatable, compounding engine?"
Common Mistakes to Flag
- Outsourcing product-market fit - Growth leaders cannot fix a business if the core product lacks a solution that customers find indispensable and retain naturally.
- Incrementalism in hyper-competitive markets - Traditional funnel tweaks take a back seat to bold innovation and core solution reinvention when competition is intense.
- Ignoring the primary growth engine - Startups often dilute efforts across many channels instead of mastering the one engine (SEO, Paid, or Viral) that fits their product mechanics.
- Measuring correlation instead of incrementality - Wasting budget on marketing spend that would have occurred anyway leads to false confidence in growth efficiency.
Deep Dive
For all 50 sourced insights from 16 guests, see references/guest-insights.md
Related Skills
- Acquisition Channels
- User Onboarding Activation
- Retention Engagement
- Referrals Word Of Mouth
© RefoundAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/growth-model of RefoundAI/lenny-skills.
- SKILL.md
- references/artifacts.md
- references/guest-insights.md
Open the folder on GitHubat commit 13598cc
Compare with similar skills
Growth Model next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Growth Model this skillRefoundAI/lenny-skills | 1.4k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Linearasgeirtj/system_prompts_leaks | 69k | — | ~653 | Automated safety check: Pass | CC0-1.0 | |
| Linearyc-software/qm | 15k | — | ~886 | Automated safety check: Pass | MIT | |
| Growth Funnelkostja94/marketing-skills | 1k | — | ~1k | Automated safety check: Pass | MIT | |
| Growth Enginesickn33/agentic-awesome-skills | 47k | 2 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Linear Issue Workflowlobehub/lobehub | 83k | — | ~1.5k | Automated safety check: Pass | Custom licence |
Similar skills
Linear
yc-software/qm
Search, read, create, and update the user's Linear issues, projects, and comments through per-user OAuth.
Growth Funnel
kostja94/marketing-skills
When the user wants to plan growth using the AARRR framework, diagnose growth bottlenecks, or map actions across the customer lifecycle.
Growth Engine
sickn33/agentic-awesome-skills
Motor de crescimento para produtos digitais -- growth hacking, SEO, ASO, viral loops, email marketing, CRM, referral programs e aquisicao organica.
Linear Issue Workflow
lobehub/lobehub
Handles Linear issues for the team: reading details and images, checking sub-issues, marking progress, labeling AI-created issues and writing completion comments.
Growth Log
affaan-m/ECC
Write growth log entries that extract reusable patterns from completed work — root cause, transferable rule, and a recognizable signal — instead of diary-style event narration, with a 4-8 sentence…
More from RefoundAI/lenny-skills
All 76 skills in this repoCustomer Interviews
RefoundAI/lenny-skills
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
Time Energy Management
RefoundAI/lenny-skills
Help users master their personal output by shifting from reactive scheduling to intentional energy management, internal trigger mastery, and proactive boundary setting.
User Onboarding Activation
RefoundAI/lenny-skills
Help users reach their first moment of core value by optimizing the first-run experience, removing friction, and aligning product design with psychological triggers.
Acquisition Channels
RefoundAI/lenny-skills
Help users identify unique distribution advantages and master the lifecycle of acquisition channels to build a sustainable engine for growth and retention.
AI Assisted Prototyping
RefoundAI/lenny-skills
Help users build functional product prototypes from natural language or visual mocks using AI coding tools.
AI Evals
RefoundAI/lenny-skills
Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.
Questions about Growth Model
What does Growth Model do?
Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business. Growth Model is an agent skill from RefoundAI/lenny-skills. Help users transition from linear funnel thinking to a loop-based growth model that identifies and optimizes the core engines of their business.
How do I install Growth Model in Claude Code?
Run `npx skills add RefoundAI/lenny-skills --skill growth-model -a claude-code`. Or copy the skill folder (skills/growth-model in RefoundAI/lenny-skills) into .claude/skills/growth-model in your project. Claude Code loads it when a task matches its description.
How do I install Growth Model in Codex?
Run `npx skills add RefoundAI/lenny-skills --skill growth-model -a codex`. Or copy the skill folder (skills/growth-model in RefoundAI/lenny-skills) into .agents/skills/growth-model in your project. Codex loads it when a task matches its description.
Can I use Growth Model in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RefoundAI/lenny-skills --skill growth-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/growth-model, .gemini/skills/growth-model, .github/skills/growth-model and .opencode/skills/growth-model in your project.
What does Growth Model need to run?
SKILL.md names no scripts, command-line tools or credentials: Growth Model is instructions for the agent only.
Does Growth Model access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Growth Model safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Growth Model use?
Growth Model is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Growth Model use?
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 61k tokens, read only when the agent opens those files.
What are the alternatives to Growth Model?
Skills that share tags, products or a category with Growth Model: Linear (asgeirtj/system_prompts_leaks, 69k stars), Linear (yc-software/qm, 15k stars), Growth Funnel (kostja94/marketing-skills, 1k stars) and Growth Engine (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Growth Model?
RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,377 GitHub stars. The repository holds 76 skills in this directory. The repository was last updated on July 16, 2026.
Source: RefoundAI/lenny-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.