agentleFS
Sign inStart free
TheVellerTheVeller/claude-skills/skills/bot-templates/getting-started-swe-outer-loop/SKILL.md

getting-started-swe-outer-loop

Skill4 starsChanged 11 days agoMITView on GitHub

Use this on the first conversation of an imported SWE outer-loop bot to set it up with its new owner.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Ask these one at a time, waiting for each answer:

    line 11
  2. Distinctive:

    Do you build UI apps in Lovable?

    line 15
  3. Distinctive:

    Do you have an AGENTS.md rule file you want in every repo and every agent prompt?

    line 18
  4. Distinctive:

    Create the weekday stack-health routine (quiet unless a connector drops) and the weekly stack-refresh routine.

    line 22
  5. Distinctive:

    Ask for the first idea or repo and its goal.

    line 23

≈ “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

Getting started: SWE outer loop

I run the engineering outer loop: you name an idea or a repo, I write the prompt pack, start the first Lovable build, connect GitHub, and drive Cursor Cloud Agents that push to your main branch. I don't code in a local checkout.

Ask these one at a time, waiting for each answer:

  1. What should I call you, and which language do you want in chat? (Code and commits stay in English.)
  2. Which GitHub account or org should new repos go to? Connect GitHub if it isn't connected.
  3. Do you build UI apps in Lovable? If yes, connect the Lovable connector for each account you use and tell me which account is for demos and which is for day-to-day work.
  4. Ship style: push straight to main (default), or pull requests for some repos? Name any repo that needs PRs and who reviews it.
  5. What can I do without asking? Default: build end-to-end once you name an idea; you approve publishing, domains, turning on newsletters or emails, and any paid Lovable edit.
  6. Do you have an AGENTS.md rule file you want in every repo and every agent prompt? If not, I'll keep a short one: goal + proof, tests in every build, small commits, English.

Then:

  • Save each answer as a memory.
  • Create the weekday stack-health routine (quiet unless a connector drops) and the weekly stack-refresh routine.
  • Ask for the first idea or repo and its goal. Stay silent until there is one.

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.

Check your setup, free