agentleFS
WhorideChickenWhorideChicken/first-playable/skills/design/SKILL.md

design

Skill3 starsChanged 32 days agoMITView on GitHub

Interactive game design interview. Turns a raw game idea into structured design documents (overview, core loop, rules, player experience) through focused questions. Use when the user wants to start a new game project, flesh out a game idea, or says /first-playable:design.

197 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use banner-design, ui-styling and 10 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.
  • seikaikyoSkill

    banner-design

    Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.

    Also in 38 projects that use this

  • MicrosoftSkill

    ui-styling

    Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.

    Also in 39 projects that use this

  • seikaikyoSkill

    brand

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

    Also in 43 projects that use this

  • mayankjain1815-commitsSkill

    infra-audit

    Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.

    Also in 3 projects that use this

  • JetBrainsSkill

    slides

    Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.

    Also in 42 projects that use this

  • AnthropicSkill

    design-system

    Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.

    Also in 49 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask 3–5 questions at a time, never more.

    line 14
  2. Very specific:

    Never silently promote PROPOSED to CONFIRMED.

    line 27
  3. Very specific:

    If the user's answers conflict with something already CONFIRMED, point out the conflict immediately instead of recording both.

    line 28
  4. Very specific:

    Write to Docs/Game/ in the user's project (create the directory if needed).

    line 46
  5. Very specific:

    Use the templates in this plugin's templates/game/ directory as the starting structure.

    line 47
  6. Very specific:

    Every rule gets a unique ID (<DOMAIN>-<NNN>) that later Feature Specs and tests will reference:

    line 62

“Common” is measured: kept by at least 6 in 10 of the 174 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 Design Interview

You are running Phase 1 of the FirstPlayable workflow: turning a game idea into design documents that later phases (scope, bootstrap, feature, verify) treat as the source of truth.

Ground rules

  • Ask 3–5 questions at a time, never more. Wait for answers before continuing.
  • Record answers incrementally into the documents below — do not wait until the end of the interview to write files.
  • Label every recorded statement with one of these statuses:
StatusMeaning
CONFIRMEDThe user explicitly decided this
PROPOSEDYou suggested it; the user has not approved it yet
TEMPORARYPlaceholder value good enough for a prototype
UNRESOLVEDNeeds a decision before implementation
EXCLUDEDExplicitly decided NOT to build
  • Never silently promote PROPOSED to CONFIRMED. Only the user confirms.
  • If the user's answers conflict with something already CONFIRMED, point out the conflict immediately instead of recording both.

Question order

Work through these topics in order. Skip ones the user has already answered.

  1. Who or what is the player? (role, perspective, fantasy)
  2. What action does the player repeat most often? (the core verb)
  3. How are success and failure decided?
  4. What choices and judgments does the player make?
  5. How does a single run/round start and end?
  6. What changes between repeated plays?
  7. Target platform and input method?
  8. Anything that must be included — or must be excluded?

Output documents

Write to Docs/Game/ in the user's project (create the directory if needed). Use the templates in this plugin's templates/game/ directory as the starting structure.

Docs/Game/
├─ GAME_OVERVIEW.md      # one-liner, genre, player role, core fun, platform, scope in/out
├─ CORE_LOOP.md          # perceive → choose → act → result → next choice, with input/feedback/risk per step
├─ GAME_RULES.md         # one rule per ID (e.g. MOVE-001) with condition/process/result/exception
├─ PLAYER_EXPERIENCE.md  # first thing to understand, feel targets, failure communication, retry drivers
├─ GLOSSARY.md           # project-specific terms, one definition each
└─ OPEN_QUESTIONS.md     # every UNRESOLVED item, so nothing silently drops

Rule format (GAME_RULES.md)

Every rule gets a unique ID (<DOMAIN>-<NNN>) that later Feature Specs and tests will reference:

## MOVE-001

- Status: CONFIRMED
- Condition: player is grounded and movement input exists
- Process: move in camera-relative input direction
- Result: character position and facing change
- Exception: input movement is not applied during knockback

Completion

The interview is done when: the core loop is written, success/failure rules exist, scope in/out is recorded, and OPEN_QUESTIONS.md lists the remaining UNRESOLVED items. Then suggest running /first-playable:review-design.

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.