agentleFS
hellocrossmanwildhellocrossmanwild/Claude-skills-tools/skills/first-ten/SKILL.md

first-ten

Skill0 starsChanged 38 days agoMITView on GitHub

Finds an app's first ten users by hand and helps write one personal message each. Use for 'how do I get users', 'help me launch', 'who should I tell' or 'write outreach messages'.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  1. Distinctive:

    Read their brief (or ask): what it does, who it's for, the problem it solves, and how it makes money.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

First ten

You're helping someone get their first ten users. The idea: launch day doesn't make a business. Distribution comes first, and the first users are ones you go and get, one at a time. Do things that don't scale.

1. Understand the app

Read their brief (or ask): what it does, who it's for, the problem it solves, and how it makes money. Play back the target user in one sentence and check it's right.

2. Who are the first ten?

Help them describe their ideal first user precisely: job, situation, the moment they feel the problem. Then ask who they already know, or are one introduction away from, who fits. Their existing network beats strangers.

3. Where do they gather?

Suggest specific places these people already are: communities, groups, forums, newsletters, events, marketplaces, and other people's audiences they could borrow (a partner, a creator, a supplier who already talks to these users). Be specific and practical; skip generic "post on social media" advice.

4. Build the list

Help them write a list of ten named people or specific places, with one line on why each fits. Save it as a simple table they can track:

WhoWhy they fitWhere / how to reachMessage sentRepliedTried it

5. Write the messages

For each person, help write one personal message: short, specific to them, about their problem not the product, with a small ask (try it, give feedback, a 10-minute call). No templates blasted to everyone, no fake urgency, no spam. Never send anything yourself: they send each one.

6. Sell before it's finished

Encourage them to start these conversations before the build is done: what people say should shape version one, and a pre-sale or waitlist proves people want it.

7. Follow up

Suggest a simple rhythm: message 2–3 people a day, follow up once after a few days, and log what people say. After ten conversations, review the patterns together and decide what to change.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.