agentleFS
CodoopCodoop/codoop-flowcabin/skills/game/SKILL.md

game

Skill0 starsChanged 4 months agoMITView on GitHub

Create, modify, validate, and package editable offline HTML/CSS/JavaScript games for Codoop Flow Cabin. Use when a user describes a small Flow Cabin game, asks to update an existing game while preserving its ID, needs an import-ready ZIP, or needs a Flow Cabin package checked for manifest hashes, safe paths, size limits, and forbidden network or host APIs.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. wormholeportal/Makone★ 27same name
    2. baney75/myelinate★ 6same name
    3. wubinKKK/private-ai-workbench★ 4same name
    4. muxammadmamajonov/dot-claude★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    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. Distinctive:

    Ask at most one question, and only when the answer changes the core game.

    line 13
  2. Distinctive:

    Treat the Skill directory as read-only.

    line 21
  3. Distinctive:

    Use another output root only when the creator explicitly requests it.

    line 31
  4. Distinctive:

    Stop animation, timers, and sound while paused.

    line 41
  5. Distinctive:

    Before packaging, ask only the triggered expert roles to review the finished package, then resolve release-blocking findings.

    line 48
  6. Very specific:

    Do not invent FlowCabinGameAPI, initialization events, or an input bridge.

    line 64
  7. Distinctive:

    Do not add frameworks, package managers, build steps, remote assets, network requests, iframes, fullscreen, Node/Electron APIs, dynamic …

    line 65

“Common” is measured: kept by at least 6 in 10 of the 3 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

Game

Build the smallest polished version of the requested game with only local, editable HTML, CSS, JavaScript, SVG, PNG, WebP, and JSON files.

Workflow

  1. Ask at most one question, and only when the answer changes the core game. Otherwise choose a sensible control scheme and visual theme.
  2. Read project-layout.md, package-v1.md, and runtime-api.md, then follow expert-orchestration.md. Use sub-agents for the bounded expert reviews when supported; keep all file edits with the main agent.
  3. Treat the Skill directory as read-only. For a new game, resolve this Skill's absolute directory and initialize the project in the creator's active coding workspace:

    python3 <skill-dir>/scripts/create_game.py <workspace> <game-id> \
      --title "<Game Title>"

    This creates <workspace>/flow-cabin-games/<game-id>/package/ and dist/. Use another output root only when the creator explicitly requests it. Replace the template visuals and rules while keeping external CSS and JavaScript files.

  4. Build for the Flow Cabin display contract in runtime-api.md. Treat the package viewport as a 420 × 560 (3:4) game stage, fill it without size caps or centering, and keep the layout responsive to viewport resize. Use native browser input. Prevent default behavior only for keys the game consumes. Keep pointer coordinates relative to the game surface.
  5. Register pause and resume through window.FlowCabinGame only when it exists. Stop animation, timers, and sound while paused; keep normal-browser preview working without the host object.
  6. Preserve manifest.json.id when modifying an existing game and explicitly increment version.
  7. Preview package/index.html in a browser at 420 × 560 and at another 3:4 size. Exercise keyboard, pointer, pause/resume fallback, restart, and resize behavior; reject clipping, letterboxing, or overflow.
  8. Before packaging, ask only the triggered expert roles to review the finished package, then resolve release-blocking findings.
  9. Package from any working directory using absolute or resolved paths:

    python3 <skill-dir>/scripts/flow_cabin_package.py \
      pack <workspace>/flow-cabin-games/<game-id>/package \
      --output <workspace>/flow-cabin-games/<game-id>/dist/<game-id>-<version>.zip
    python3 <skill-dir>/scripts/flow_cabin_package.py \
      validate <workspace>/flow-cabin-games/<game-id>/package
  10. Report the source directory, ZIP path, controls, and the remaining manual step: import the ZIP into Codoop Flow Cabin and verify its cover, gameplay, pause, and resume.

Do not invent FlowCabinGameAPI, initialization events, or an input bridge. Do not add frameworks, package managers, build steps, remote assets, network requests, iframes, fullscreen, Node/Electron APIs, dynamic loading, audio, fonts, or WASM.

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.