agentleFS
MicrosoftKnown publishermicrosoft/amplifier-acp-minecraft/skills/minecraft-server-setup/SKILL.md

minecraft-server-setup

Skill1 starsChanged yesterdayMITView on GitHub

Set up, connect, verify or upgrade a Minecraft server and independent ACP players, including Java/Bedrock/Xbox LAN gateways and installation-owned updates. Use for server/player operations and troubleshooting; use the separate skin skill for artwork.

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:

    Read the installation requirements.

    line 14
  2. Distinctive:

    Use available configuration and connected evidence before asking the user for missing details.

    line 21
  3. Distinctive:

    Use the requirements in staging and routes, behavior choices, [layered

    line 47
  4. Distinctive:

    Use the evidence requirements in verification and handoff to close the requested operation.

    line 62
  5. Distinctive:

    When a setup failure teaches a reusable lesson, update the smallest relevant reference or tested helper.

    line 68

≈ “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

Minecraft server and player setup

Operate the user's requested server and installations, preserving existing worlds, identities and work. This skill is portable across ACP engines and owners. It does not assume the author's hosts, ports, accounts, model, systemd layout or policies.

Inspect before selecting a path

Read the installation requirements. Determine whether the request is for a new world, an existing world, a player connection, a gateway repair, behavior policy, or an update. Inventory the actual versions, service owners, listeners, routes, saved sessions and in-flight work before changing an existing installation. Resolve current coordination receipts by request ID and time; delayed notes do not reopen completed holds or authorize duplicate restarts.

Use available configuration and connected evidence before asking the user for missing details. Proceed within the authorization already provided. Ask only for material choices, external account authorization or missing access; do not turn routine reversible staging into another approval flow.

Route to the needed reference

  • Fresh server, adding a player, or an existing-host upgrade: server setup.
  • Xbox / Bedrock / LAN visibility or authentication: Xbox LAN. Discovery, transport and real login are separate. Preserve the authenticated human route; never expose the agent route.
  • Natural human requests, limits, responsiveness or activity: human-led play, task intake and, if needed, completion-bound helpers.
  • Updating source/dependencies, engine or shared components: installation updates.
  • Protocol, tools, context or recovery specifics: read only the relevant section of the adapter reference and the SDK boundary.
  • Appearance: agent-skin skill. Screenshots: setup guide.

Apply the installation boundary

Use the requirements in staging and routes, behavior choices, layered verification and recovery. They define what must survive and what the requested operation permits. This skill navigates those requirements; it does not add a second authority or lifecycle policy.

For example, fixing Xbox discovery normally affects its human gateway, while a player source update uses that player's lifecycle participant. Choose the smallest relevant operation from the inspected topology, rather than restarting everything. A fresh no-start installation and a used connection have different session-verification paths; follow the applicable reference.

Close with meaningful evidence

Use the evidence requirements in verification and handoff to close the requested operation. Report what was actually checked and what still requires the person's console or account. Keep private installation material out of the publication checkout.

When a setup failure teaches a reusable lesson, update the smallest relevant reference or tested helper. Keep examples illustrative and link to the governing requirement instead of adding another definition here or in the README.

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.