agentleFS
phnx-labsphnx-labs/rush-mcp/skills/get-started/SKILL.md

get-started

Skill0 starsChanged 4 days agoMITView on GitHub

First run with Rush. Use right after the plugin is installed, or when someone asks what Rush is, how to start, or how to hand it their first task.

32 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 0

    Distinctive

    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:

    Check the connection and ask: Call list_repositories. If the client asks the person to sign in, tell them to finish signing in to Rush (in …

    line 11

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “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

Get started with Rush

Take the person from install to one finished task in three short turns. Never ask for a password, token or API key in chat, and never invent a result.

  1. Check the connection and ask. Call list_repositories. If the client asks the person to sign in, tell them to finish signing in to Rush (in Claude Code: /mcp, then Rush) and stop until they have. Then say in one sentence what Rush is: an agent that does a task in its own cloud computer and hands back the result with a record of what it did. Ask one question: "What would you like done? It can be on one of your repositories, or need none." If the list is empty, add that a task on code needs the Rush GitHub App on that repository (https://cloud.getrush.ai/console/settings/?section=connections), or, for a gitlab.com project, a GitLab sign-in (connect_account with type app and name gitlab).
  2. Start it. Confirm the repository against the list when the task names one. Then follow the hand-off-a-task skill: write the task with everything the agent needs, start it, say it takes a few minutes, and wait until it settles.
  3. Report and close. Give the answer, the pull request link if there is one, and any files it made. Then say how to continue: ask for the next task in plain words, reply to this one to keep going in the same computer for 7 days, and see every run at https://cloud.getrush.ai.

Runs use the Claude or ChatGPT account the person connected to Rush; without one, Rush's models cover a first try. If the start is refused, use the table in hand-off-a-task under "When Rush refuses".

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.