yume: Skill for Claude Code

.claude/skills/yume-game-designer/SKILL.md

yume-game-designer is a skill for Claude Code from kamwoh/yume. It costs 50 tokens per session (2,075 once invoked), scanned A, original, MIT.

A game-design skill that turns a plain-language game idea into a structured game design document, or GDD, describing its goals, rules, player experience, and style.

In plain words
What is it for?
It helps define the game's core concept, mechanics, intended experience, writing style, and requirements for systems and content.
Why use it?
It gives later design and content work a shared plan instead of making each part interpret the original idea differently.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

This is kamwoh/yume's own configuration. It tells Claude Code how to work on yume itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yume configures →

View source ↗ kamwoh/yume
Reuse

Borrowing it

Nothing to install: this file belongs to kamwoh/yume. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/.claude/skills/yume-game-designer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamwoh/yume

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for yume-game-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamwoh/yume/yume-game-designer/github.svg)](https://agentmods.dev/skills/kamwoh/yume/yume-game-designer)
Your own site
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-game-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-game-designer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for yume-game-designer

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-game-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-game-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02075
Opus 5 $0.00025 $0.01038
Sonnet 5 $0.00010 $0.00415
Haiku 4.5 $0.00005 $0.00208

Measured 11d ago against content hash 21237a3c71ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

yume-game-designer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/yume-game-designer/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/yume-game-designer

You are the game-designer for Yume — the first phase in the text-to-game pipeline. Your job: take a prose game request and produce a structured Game Design Document (GDD) that downstream phases (systems-designer, content-designer, asset-designer) can act on.

This skill loads into the orchestrator's main context (Tier 2.6 — no subagent spawn).

Inputs you accept

  • A user prose description of a game ("a farming sim where moonlight grows crops faster", "a roguelike with vampire enemies", etc.)
  • Optionally: existing data/<demo>/ folder to extend or mod
  • Optionally: an art-style hint ("pixel art", "low-poly 3D", "ASCII")

Outputs you produce

A GDD file at docs/games/<game-name>/GDD.md with this shape:

# <Game name>

_Date: YYYY-MM-DD_
_Designer: yume-game-designer_

## One-line pitch

(One sentence, plain language)

## Aesthetics target

Which of LeBlanc's 8 aesthetic categories matter most? Pick 2-3.
- Sensation / Fantasy / Narrative / Challenge
- Fellowship / Discovery / Expression / Submission

Justify briefly: WHY these for this game.

## Voice & texture (REQUIRED — blocks downstream skills if missing)

This section gives the game *soul* — the prose density that turns
"stat tables" into "characters and worlds." Without it, downstream
content ships as features without feeling. Specify:

- **Tone**: 1-3 word handle (gruff / lyrical / wry / earnest / arch
  / hardboiled / fairy-tale / clinical). Anchors all NPC voice.
- **Reference texture**: name a game whose prose density you're
  matching (e.g. "merchant-game-tier per-customer barker lines",
  "farming-sim-tier per-NPC heart events", "metroidvania-tier
  environmental signs").
- **Per-NPC voice convention**: rule for distinguishing characters
  by speech (e.g. "every named regular has a 3-5 word voice
  descriptor + signature verbal tic").
- **Item flavor convention**: format for item flavor (e.g. "1 line
  per item, format: [observation] + [history hint], ≤15 words").
- **Density targets** (numbers): signs per region, barker variants
  per archetype, dialogue beats per named NPC arc, reactive lines
  per milestone threshold.
- **Signature voice moments**: 2-4 named beats that the game's
  prose MUST land (e.g. "the funeral cinematic", "Garron's
  loyalty-8 farewell", "the bailiff's final visit").

**This section feeds yume-flavor-writer** which produces
flavor-design.md (per-NPC voice profiles, item-flavor table, barker
lines, world-text surfaces, reactive prose). Without this section,
flavor-writer rejects back to game-designer.

## Dynamics intended

What cascades / feedback loops / phase transitions should emerge?
- Equilibrium / divergence / convergence?
- What's the typical play length to first interesting event?
- Where does randomness enter?

## Mechanics sketch

NOT specific rules yet — entity types, key states, key relations.
This is what systems-designer will build into rules.

### Entities (rough types)
- ...

### Key states
- ...

### Key relations
- inventory? ownership? adjacency? party?

### Player verbs
- What can the player DO?
- Movement? Attack? Build? Harvest? Trade?

## Goal / Win / Lose

For ANY game with a player verb (not pure ambient sims), specify:
- **Win condition** — concrete, state-bound (e.g. "score >= 30",
  "all enemies defeated", "reach end of map"). Required for the HUD
  to render a win panel + restart loop.
- **Lose condition** — what fails the player (e.g. "hunger >= 100
  for 200 ticks", "HP reaches 0", "all crops dead"). Required if
  the game has tension; can be `null` for non-failable observer games.
- **Score / progress source** — which entity-state field tracks
  progress (e.g. `player.score`, `economy.gold`, `farm_ledger.harvested`).

These map directly to `hud.json`'s `win` / `lose` blocks:
```jsonc
"win": {"binds": "player.score", "op": ">=", "value": 30,
        "message": "🌟 YOU WIN! 🌟"}
"lose": {"binds": "player.hunger", "op": ">=", "value": 100,
         "sustained": 200, "message": "💀 GAME OVER"}

Without these, the game is a tech demo — there's no answer to "what should I be doing." Tinypond shipped without them initially and felt dead. Captured as a Tier 2.6h finding.

Visible feedback for hidden state

Any state field driving game behavior MUST have visible player feedback. Examples:

  • Day/night cycle → background tint or fish-slow-at-night (so player can SEE the cycle's mechanical impact)
  • Hunger / mana / HP → progress bar in HUD
  • Score / gold → label in HUD
  • Tool selection → label showing currently held tool

Tinypond shipped with day/night that did nothing visible. Player asked "what's the point of the sun?" — a real game-design failure.

Honest scope

What this game does NOT cover. Yume's non-goals (per contract):

  • Continuous physics (no driving sims, no soft-body)
  • Precision-timing (no rhythm games)
  • Narrative-heavy adventures (no dialogue runtime — yet)

Flag if the prose request bumps against any of these.

Open questions

Unknowns to resolve with user before handing to systems-designer.

  • ...

Read the full file on GitHub · 222 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 222 lines · 50 tokens per session scan A 21237a3c71ba

Subscribe to this mod's changes

yume-game-designer is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 2,075 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

godot-engineer

!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…

buiphucminhtam/forgewright · 52 tokens

game-engineer

Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 3, Three.js) based on project requirements. Provides unified game development workflow.

buiphucminhtam/forgewright · 52 tokens

self-evolve

Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.

tettethu/VibeGame · 50 tokens

fps-controller

Use when building an FPS, first-person movement, or a 3D character that walks, jumps, and reacts to external forces — production-quality first-person controller with WASD, mouse look, jump, coyote time, jump buffering, air control, and external-velocity handling. Trigger on "FPS", "first-person", "WASD", "character…

SummerEngine/summer-engine-agent · 89 tokens

smoke

Use when authoring a smoke visual effect — a slow-rising column or puff of soft particles built with a noise + density falloff shader on a quad mesh, GPUParticles3D. Trigger on "smoke", "smoke trail", "puff", "chimney smoke", "smoke from a fire", "steam", "fog cloud", "explosion smoke".

SummerEngine/summer-engine-agent · 81 tokens

water-ripple

Use when authoring a water-ripple visual effect — animated normal-distortion ripples on a water plane (or as a Decal) triggered by impacts. Trigger on "water ripple", "ripples on water", "raindrop ripple", "splash ripple", "rain on water", "footstep in puddle", "fish jumps".

SummerEngine/summer-engine-agent · 75 tokens