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

prototype

Skill9 starsChanged 7 months agoMITView on GitHub

Quick prototype workflow — minimal viable implementation, no production standards, README with hypothesis. Code goes in prototypes/, never imported from src/.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test 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

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 12 projects that use this

  • +5 more from lilangMax
  • +2 more from CoralGame

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 6

    Distinctive

    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:

    Only build what's needed to test the hypothesis

    line 30
  2. Distinctive:

    Write code that answers the question.

    line 44
  3. Distinctive:

    Add type annotations (unless they help)

    line 45
  4. Distinctive:

    Use clear variable names (so future-you understands)

    line 52
  5. Distinctive:

    After running, update the README:

    line 57
  6. Distinctive:

    Bad idea: Document learnings, archive the prototype, move on

    line 90

“Common” is measured: kept by at least 6 in 10 of the 178 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

/prototype — Rapid Prototyping Workflow

Delegate to: luau-gameplay-programmer or luau-systems-programmer (depending on scope)

Purpose

Prototypes are throwaway code to test an idea quickly. They are NOT production code.

Rules

  • Prototypes live in prototypes/<prototype-name>/
  • Prototypes NEVER import from src/
  • Prototype code does NOT need to meet production standards
  • Prototypes require a README.md explaining the hypothesis
  • Prototypes are NOT graduated directly to src/ — if the idea is good, rewrite cleanly

Steps

1. Define the Hypothesis

Ask the user:

  • "What are we testing?"
  • "What's the question this prototype answers?"
  • "What would 'success' look like?"
  • "What's the time budget?" (default: 2-4 hours)

2. Scope Ruthlessly

  • Only build what's needed to test the hypothesis
  • Skip: polished UI, data persistence, multiplayer (unless core to hypothesis)
  • Focus: the thing that's being questioned

3. Set Up Prototype Directory

prototypes/
└── <prototype-name>/
    ├── README.md        # Hypothesis, how to run, findings
    ├── src/             # Prototype Luau files
    └── assets/          # Any placeholder assets

4. Build the Minimum

Write code that answers the question. Do NOT:

  • Add type annotations (unless they help)
  • Wrap in pcall (unless necessary for the question)
  • Write tests
  • Worry about cleanup
  • Optimize performance

DO:

  • Use clear variable names (so future-you understands)
  • Comment the KEY decisions
  • Make it runnable (Rojo or manual Studio import)

5. Document Findings

After running, update the README:

# Prototype: [Name]

## Hypothesis
[What we were testing]

## How to Run
1. [Setup steps]
2. [Run steps]

## What We Learned
- [Finding 1]
- [Finding 2]
- [Unexpected result]

## Go / No-Go
**Verdict**: [Good idea / bad idea / needs more research]

## If Go, Next Steps
1. [How to translate this into production]
2. [What specialists are needed]
3. [What systems it affects]

## If No-Go
- [Why it didn't work]
- [Alternative approaches to consider]

6. Decide

User decides:

  • Good idea: Schedule proper implementation (rewrite, not copy-paste)
  • Good idea with tweaks: Iterate the prototype OR move to production planning
  • Bad idea: Document learnings, archive the prototype, move on
  • Inconclusive: Decide if more prototyping is worth the time

Anti-Patterns

  • Prototype sprawl (spending weeks on a "prototype")
  • Importing prototype code into production without rewrite
  • Skipping the README and losing the findings
  • Testing multiple hypotheses in one prototype (hard to learn from)

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.