agentleFS
KonHKonH/GlobalStrategy/.claude/skills/unity-e2e-run/SKILL.md

unity-e2e-run

Skill3 starsChanged 2 months agoMITView on GitHub

Drive GlobalStrategy through a live Unity Editor play session via the .e2e file handshake. Use when verifying or debugging a change against the running game. Starting a run needs no confirmation.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Before dropping a request, run the unity-plugins skill (python scripts/unity/ensure_plugin_dlls.py) so gitignored Assets/Plugins/Core/ DLLs …

    line 8

≈ “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

Unity E2E run (GlobalStrategy)

Before dropping a request, run the unity-plugins skill (python scripts/unity/ensure_plugin_dlls.py) so gitignored Assets/Plugins/Core/ DLLs exist, and so Unity MCP is pinned to this checkout. Another GlobalStrategy Editor will not pick up this .e2e/ handshake. Then invoke cc:unity-e2e-run. Project specifics:

  • Handshake root: .e2e/ (gitignored). Drop a RunRequest at .e2e/requests/<runId>.json.
  • Committed flows: Docs/E2E/flows/new_game_to_map.json and Docs/E2E/flows/load_save_to_map.json. Pass "script": "new_game_to_map" or "script": "load_save_to_map".
  • Scratch scripts: .e2e/scratch/<name>.json.
  • protocolVersion is 1 (GS.Game.E2E.E2EProtocol.Version).
  • Scenes / screens: MainMenu, CountrySelection, Map. Gallery is not drivable.
  • In waitFor, prefer those scene names. The runner accepts a match on either the active scene or the guessed UI document. Step snapshots use a different screen field: the top visible PanelRenderer GameObject when it is not named like the scene (e.g. GameHUD on Map, SelectCountryUI on CountrySelection, LoadWindowUI when the load window is open). Do not copy a snapshot screen into waitFor unless you mean that document.
  • The watcher refuses the request if any open scene is dirty (An open scene is dirty; refusing so restoration cannot destroy unsaved work.). Save or discard before dropping a request.
  • Org ids come from Assets/Configs/organizations.json (OrganizationId). Default org is the first entry; name it in the report when unset.
  • Commands are the src/Game.Commands set, executed through src/Game.Commands.Text the same way as the web terminal.
  • Starting a run needs no confirmation.

Example request:

{
  "protocolVersion": 1,
  "runId": "verify-1",
  "script": "new_game_to_map",
  "initiator": "agent"
}

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.