agentleFS
Sign inStart free
Fadi88Fadi88/one-man-startup/.cursor/rules/skill-setup.mdc

one-man-startup / rules

Cursor rule16 starsChanged 2 days agoMITView on GitHub

The setup interview that customises this template for one founder's company by region, domain, audience, customer size, stack, gates, team, budget and licence, and writes project.toml. Use at the start of a new company or when any of those change.

We split this skill-setup.mdc into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run skills/grilling/ over the interview tree, in rounds, each question with a recommended answer and worded for the founder's level …

    line 10
  2. Distinctive:

    When setup runs again later (a new region, market, stack or team), skip step 1 and ask only the branches that changed.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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-setup.mdc
---
description: "The setup interview that customises this template for one founder's company by region, domain, audience, customer size, stack, gates, team, budget and licence, and writes project.toml. Use at the start of a new company or when any of those change."
alwaysApply: false
---

<!-- Generated by tools/sync_adapters.py from skills/setup/SKILL.md. Edit the source, not this file. -->

# Setup

Run `skills/grilling/` over the interview tree, in rounds, each question with a recommended
answer and worded for the founder's level (`skills/founder-voice/`). Facts you can look up (the
founder's git identity, an existing codebase's stack, a region's data protection law) you look
up. Write nothing until the founder confirms the summary.

Each step is its own file. Open the one you are on, in order:

1. **Check the computer**: `skills/setup/1-check-tools.md`. Git and Python, and whether the
   repository is public, before round one.
2. **The interview**: `skills/setup/2-interview.md`. The tree of questions and what unlocks what.
   Its licence question uses `skills/setup/licences.md`, which explains the options.
3. **Write it down**: `skills/setup/3-write.md`. Every file the answers settle.
4. **Finish**: `skills/setup/4-finish.md`. Clean out the template's own content, write the
   licence, run the checks, show the founder, commit on their go.

When setup runs again later (a new region, market, stack or team), skip step 1 and ask only the
branches that changed. When the founder asks to publish (a website, an app, a release), that is
the publish branch: say what will go public and what it costs, and set `[publish] enabled =
true` on their go; `devops` then adds the publishing workflow.

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.

Reviews can't be read right now.

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.

Check your setup, free