agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/design-system/SKILL.md

design-system

Skill9 starsChanged 7 months agoMITView on GitHub

Create a per-system GDD. Interactive flow — select system from index, then generate a comprehensive design doc through a structured conversation.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-level and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +1 more from CoralGame
  • +6 more from lilangMax

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Update design/gdd/systems-index.md to mark this system as "In design" or "Ready for implementation."

    line 89
  2. Very specific:

    Run /design-review on the new GDD to verify quality

    line 93

“Common” is measured: kept by at least 6 in 10 of the 175 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

/design-system — Per-System GDD Creation

Delegate to: systems-designer (with game-designer for creative direction)

Prerequisites

  • design/gdd/systems-index.md exists (run /map-systems if not)
  • design/gdd/master-gdd.md exists (run /gdd if not)

Steps

1. Select the System

Present options from the systems-index:

  • Systems without a GDD (prioritize these)
  • Systems with outdated GDDs (mark for update)
  • Or, ask the user for a new system name

2. Gather Design Intent

Work through each section via structured questions:

Overview & Purpose

  • "What is this system in 2-3 sentences?"
  • "What player need does it serve?"
  • "How does it fit into the core loop?"

Core Mechanics

  • "How does the player interact with this system?"
  • "What are the key inputs and outputs?"
  • "What makes it fun / engaging?"
  • Walk through typical player interactions step-by-step

Data Schema

  • "What needs to persist?"
  • "What's ephemeral (per-session)?"
  • "Who owns the data — server or client?"
  • Design the DataStore schema (or delegate to datastore-architect)

Client-Server Split

  • "What runs on the server?"
  • "What runs on the client?"
  • "What's server-authoritative (game state) vs. client-authoritative (visuals/input)?"

Remotes

  • "What Client → Server calls are needed?"
  • "What Server → Client updates?"
  • "Anything high-frequency that should be UnreliableRemoteEvent?"
  • Delegate detail to remotes-networking-specialist

Player-Facing UI

  • "What does the player see?"
  • "What UI elements exist (HUD, menus, modals)?"
  • "ASCII wireframe or description?"

Edge Cases & Error States

  • "What happens when:
    • Player has zero resources?
    • Player has max resources?
    • System is used rapidly in succession?
    • Player disconnects mid-action?
    • Server restarts during use?
    • DataStore is unavailable?
    • Network lag occurs?"

Balancing Parameters

  • "What values should be tunable?"
  • "What's the formula?" (write it explicitly, no "balanced appropriately")
  • "Min / max / default for each parameter?"

Integration Points

  • "Which other systems does this depend on?"
  • "Which systems depend on it?"
  • "Any shared data or shared modules?"

3. Draft the GDD

Using .claude/docs/templates/gdd-system.md as the skeleton, fill in from the gathered intent.

4. Present for Review

Show the complete draft to the user for review.

5. Iterate

Apply feedback, present updated draft, repeat until approved.

6. Save

On approval, save to design/gdd/<system-name>-gdd.md. Update design/gdd/systems-index.md to mark this system as "In design" or "Ready for implementation."

7. Next Steps

Suggest:

  • Run /design-review on the new GDD to verify quality
  • Schedule implementation via /sprint-plan
  • Link related GDDs

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.