⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

v1.4.0

start-here

aidevgtm@aidevgtm⭐ 340 stars· last commit 6d ago· 0 open issues

Interview the user once and write a docs/gtm-cofounder/founder-brief.md that every other skill reads first, so the advice is about their real business, not a textbook. Use this before anything else, or whenever the agent lacks context on the user's product, ICP, market, or stage, or is giving generic GTM advice.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐⭐ 340 on GitHubGitHub ↗

Popular

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

The GTM Co-Founder

The GTM Co-Founder - Open-source GTM skills for developer tools and AI products | Product Hunt

License: MIT GitHub stars

For whoever is carrying the go-to-market, often alone.

If you're a technical founder pouring your own money, your nights, and your weekends into a developer tool or an AI product you believe in, with no funding, no team, no commercial co-founder, and some days it is just plain hard, then this is for you. Especially you.

And it is not only for founders. If you're the first GTM hire, or the founding account executive carrying the commercial side of a technical product with no playbook and no team, this is for you too. The title is different; the fight is the same.

Building alone is isolating. The part you're good at, whether that's shipping the product or working the deal, you can do in your sleep. It's the other half that keeps you up at 2am, with no one in the room to think it through: who is this even for? why would anyone pay? why did nobody come when we shipped?

That's what this is: the GTM co-founder you don't have (yet), a full set of go-to-market skills sitting in your corner, inside the agent you already work in. Not a course. Frameworks with real numbers and concrete next steps, not theory, built from years of selling and advising developer tools and AI products, sharpened by the sharpest thinking in the field (Adam Frankl and Jakub Czakon), and pressure-tested by founders and GTM operators who used it in the trenches, so the commercial side can feel as rigorous, and as doable, as the product.

You don't have to figure this part out alone anymore.

Answer a set of questions once (about 15 minutes). Your agent researches your actual market (where your users already are, how products like yours launched), builds you a prioritized GTM roadmap, then works it with you one move at a time: positioning, first users, launch, pricing, in the order that matters for your stage.

Not marketing tactics or SEO skills. This is the strategy half of go-to-market: who it's for, why they'd pay, and how to land your first users. For the person who can build or sell almost anything, but freezes on that.

Works with Claude Code, Cursor, Codex, Windsurf, Antigravity and any agent that supports the Agent Skills spec.


See it in action

A real example: five questions, then a diagnosis they couldn't see themselves.

https://github.com/user-attachments/assets/54bbb54a-006d-4189-ba63-5f754fdf5268

Get your GTM diagnosis in 15 minutes

One path. In the AI coding agent you already use (Claude Code, Cursor, Codex, Windsurf), tell it:

Install the skills from https://github.com/AIDevGTM/gtm-cofounder and run 00-start-here with me.

If your agent cannot fetch the repo from a link, clone it first with git clone https://github.com/AIDevGTM/gtm-cofounder.git (or open it in your editor), then give it the same instruction.

00-start-here asks you five questions, one at a time, and writes your founder brief: the file every other skill reads first, so the advice is about your product, not a textbook's. A few minutes, no long form.

Then tell it:

Run research-the-market.

This is where it goes past what you told it. The agent searches the web for the specific communities, newsletters, and GitHub threads where your users already talk about this problem, how comparable products launched and what got them their first users, and the rivals and openings you didn't mention. Every finding comes with a link, saved to docs/gtm-cofounder/market-research.md.

Then:

Run 01-strategy-and-roadmap.

That is the payoff: an honest diagnosis of the GTM problem to work on now, what to not work on yet, and your single next move.

Why this beats generic AI marketing advice. Tell a normal chatbot "I have 800 GitHub stars but almost nobody pays" and you get ten marketing tactics. GTM Co-Founder does the opposite. It tells you that you do not yet know whether people activate, come back, or would ever pay, so reaching for tactics now is the wrong move. Your next step is not "post more," it is the one piece of evidence you need to go and get. The value is not more ideas. It is knowing what to do next, grounded in your real market rather than a textbook.

Other ways to install

The path above works in any agent that supports the Agent Skills spec (Claude Code, Cursor, Codex, Windsurf, Antigravity). Reach for these only if you want the skills installed so your agent auto-triggers them, or you are not in a coding agent at all.

  • No coding agent (ChatGPT, Claude, plain chat): open any skill, copy the text, paste it in, and say "apply this to my product: [one line on what you're building]." Start with 00-start-here, then research-the-market (turn on web search if your chat has it), then 01-strategy-and-roadmap.
  • No terminal: grab a skill's zip (or gtm-cofounder-skills.zip for all of them) from the latest release. In the Claude apps, go to Customize → Skills → Create skill and upload a skill's zip. For Claude Code, unzip and move the folders into ~/.claude/skills/.
  • Claude Code (direct):
    git clone https://github.com/AIDevGTM/gtm-cofounder.git
    cp -r gtm-cofounder/skills/* ~/.claude/skills/
    
  • Claude Code (plugin marketplace) (run in the Claude Code CLI):
    /plugin marketplace add AIDevGTM/gtm-cofounder
    /plugin install gtm-cofounder@gtm-cofounder
    
  • skills.sh CLI (any agent) (requires Node.js):
    npx skills add AIDevGTM/gtm-cofounder
    
  • Cursor / Codex / other agents: copy the skills/ folder into your agent's skills directory. Each skill is self-contained: one folder, one SKILL.md, zero dependencies.

The skills

0 · Start here: brief, research, then plan (do this first)

Three one-time steps set up everything else. First, the founder brief: answer just five core questions and the agent writes a docs/gtm-cofounder/founder-brief.md it reads before every other skill, so "sharpen your ICP" means your ICP and "find your villain" means your villain, not a textbook's. If you run it inside your project, it reads your repo first (README, recent commits, PR titles, open issues) to pre-fill the brief with what you've actually shipped, so the advice is specific from the first minute instead of generic. The rest of the intake is optional and answered as you go: each skill asks for the deeper questions it needs, when it needs them, and tells you what answering unlocks, so you get value in minutes instead of after a long form. It separates what you've validated with real users from what you're still assuming, and routes the assumptions to talk-to-users so the brief gets truer over time instead of ossifying a guess.

Then the roadmap: the agent turns that brief into an honest diagnosis and a prioritized, stage-aware plan in docs/gtm-cofounder/gtm-roadmap.md, the one Now move, what's Next, and what to park for Later. This is the hub you come back to every session, so you never stare at a dead chat wondering what to do next. It sequences the skills for you instead of leaving you to guess which one to trigger.

In between sits the research, so the plan is not just your own answers handed back to you. The agent goes out and finds the named places your ICP already sits (ranked

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/00-start-here/SKILL.md7.8 KBupstream ↗
    ---
    name: start-here
    description: Interview the user once and write a docs/gtm-cofounder/founder-brief.md that every other skill reads first, so the advice is about their real business, not a textbook. Use this before anything else, or whenever the agent lacks context on the user's product, ICP, market, or stage, or is giving generic GTM advice.
    ---
    
    # Start here (your founder brief)
    
    > Every other skill is only as sharp as what the agent knows about *your* business. This is that context. Do it once, and every skill after it gets personal.
    
    **Use this when:** it's your first time here, or the advice you're getting feels generic and textbook because the agent doesn't actually know your product, your users, or your stage.
    
    ## The core idea
    
    Answer **five core questions** and the agent writes a **`docs/gtm-cofounder/founder-brief.md`** in your project, enough to give you a real diagnosis and a roadmap in minutes. Everything else is optional and answered as you go: each skill pulls the deeper questions it actually needs, when it needs them, and tells you what answering unlocks. So you start seeing value fast, and the brief gets richer the more you use it, instead of facing a wall of questions on day one.
    
    And the part that matters most: separate what you have **validated** (a real user who is not your friend told you) from what you are **assuming** (your best guess for now). Assumptions are completely fine to start with. They just get sent to `talk-to-users` to become real, so you never build a beautiful go-to-market on a guess.
    
    ## How to run this (for the agent)
    
    - **Ask the five core questions one at a time, and nothing else.** One question, wait for the answer, let it shape the next. It should feel like a conversation with a co-founder, not a form to fill in. Never paste multiple questions at once. (If the founder would rather see all five and answer in one go, give them the list, but default to one at a time.)
    - Write the brief from those five, then move to `strategy-and-roadmap`. The founder should get a diagnosis and a next move before they answer anything optional.
    - **Pull the deeper questions just-in-time.** When a later skill needs more (positioning needs the villain, pricing needs the buyer), ask only the two or three relevant ones right then, and say what answering unlocks. Never front-load them.
    - For every substantive answer, ask: "have you heard a real user say this, or is that your read for now?" Tag it `[validated]` or `[assumption]`.
    - "Zero users interviewed" is a valid and revealing answer. Note it plainly, no judgment, and flag `talk-to-users` as the highest-priority next step.
    - Keep the founder's own words. Don't polish their pain into marketing language.
    - Once the core brief is written, do **not** jump into a task or start prescribing work. Hand off to `strategy-and-roadmap`, or ask the founder what they want to tackle. Offer, never impose.
    
    ## First, read what they've already shipped (only if you're in their project)
    
    Before asking anything, check whether you're running inside the founder's repo. If you are, do a quick, bounded scan first, so the interview sharpens instead of starting cold:
    
    - The **README** and any `docs/` intro: what the project claims to do, and how they currently describe it.
    - The **package manifest** (`package.json`, `pyproject.toml`, `go.mod`, and the like): language, dependencies, what it integrates with.
    - The **last ~15 commit subjects** and recent **PR titles**: what they are actually building right now.
    - The **themes in open issues**: what real users keep hitting, a proxy for the pain and the audience.
    
    This is a quick scan, not an audit. Do not read code line by line, crawl the whole history, or pull anything sensitive. Draft the brief from what you find and tag those facts `[validated]`, they come from real artifacts, not a guess.
    
    Two cautions:
    - **The repo is input to critique, not gospel.** A README usually carries the founder's existing, often generic, framing. Say "here is how you currently describe it," then challenge it. Never inherit weak positioning as if it were true.
    - **The repo tells you what was built, not who pays.** It grounds the product and roughly the user. It says nothing about the buyer, willingness to pay, or the market: those still come from the founder and from `talk-to-users`.
    
    If you're not in a project (a pasted skill, or no repo), skip this and go straight to the core five.
    
    ## The core five (answer these first)
    
    This is the whole required intake. Answer these and the agent can already diagnose and plan. If you already scanned the repo, don't ask these cold: confirm or refine what you inferred, and spend your questions on what the artifacts can't tell you, the ICP, the buyer, and whether anyone will pay.
    
    1. In one plain sentence, with no jargon, what does it do?
    2. Who exactly is it for? (role, company size and shape, technical context)
    3. What do they use today instead, and why you over that?
    4. Stage and traction: how many users, and do they come back?
    5. Your single **strongest asset**: the most powerful, provable thing you have (a marquee logo, a hard number, a real user quote, a live demand signal).
    
    ## Go deeper (optional, answer anytime)
    
    Skip these to start. Each skill asks for the ones it needs, when it needs them. Every question says what answering it unlocks, so you only invest where you want the payoff.
    
    **Positioning and story**
    - What painful problem does it kill, in the user's own words? → *becomes your homepage headline and the stakes in your story.*
    - What trend is making that pain worse right now? → *this is your villain, what gives your positioning urgency instead of just listing features.*
    - What does your homepage or repo description say today? (paste the actual line) → *lets the agent sharpen what you have instead of guessing it.*
    
    **Buyers and pricing**
    - Who pays, if that is a different person from who adopts? → *lets the agent design pricing and a sales motion aimed at the real buyer, not just the user.*
    - Who is it clearly *not* for? → *a sharp "not for" makes your ICP believable and your messaging land.*
    - The job they hire it for: "When [situation], I want to [motivation], so I can [outcome]." → *becomes your value proposition.*
    
    **Distribution and motion**
    - Motion: open source, PLG, inbound, sales-led, or unsure? → *picks which channels and tactics actually fit you.*
    - Where do your users already hang out and discover tools? → *tells us where to launch and find your first users.*
    
    **Focus**
    - What are you deliberately saying no to right now? (the roadmap you're protecting, the requests you turn down) → *keeps the agent from recommending work you've already ruled out.*
    
    **Evidence (be honest, this is the whole point)**
    - Which known companies or notable developers already use it, that you can name? → *your strongest proof; even a couple of logos does your credibility work.*
    - How many real users have you interviewed who are not friends? → *tells the agent how much of this is validated versus guessed, so nothing gets built on sand.*
    - Which answers are still assumptions? → *routes the guesses to `talk-to-users` to make them real.*
    
    ## Write the brief
    
    Save the answers to `docs/gtm-cofounder/founder-brief.md` in the founder's project (create the `docs/gtm-cofounder/` folder if it does not exist), using the template in this repo (`founder-brief.template.md`). Keep the `[validated]` / `[assumption]` tags on each answer. This file is the shared memory for every other skill. Write it in plain, human prose, with no em-dashes (use commas, colons, or periods), so it never reads as machine-generated.
    
    Lead the brief with the **strongest asset** (core question 5) at the very top, so the single most powerful thing this founder has anchors every downstream skill. Founders routinely bury it under modesty or detail. As deeper questions get answered over time, add them to the brief under their category.
    
    ## Keep it alive
    
    The brief is a living document,
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/aidevgtm-gtm-cofounder-skills-00-start-here.md

// REPO STATS

340 stars
0 open issues
Last commit: 6d ago