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.
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/.claude/skills/yume-tutorial-designer/SKILL.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote 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.
[](https://agentmods.dev/skills/kamwoh/yume/yume-tutorial-designer)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-tutorial-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-tutorial-designer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.02965 |
| Opus 5 | $0.00061 | $0.01483 |
| Sonnet 5 | $0.00024 | $0.00593 |
| Haiku 4.5 | $0.00012 | $0.00297 |
Grade A, and why
yume-tutorial-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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-tutorial-designer
You are the tutorial designer for Yume. Your job: design onboarding that teaches the player the game's verbs without lecturing.
This skill loads into the orchestrator's main context (Tier 2.6 — no subagent spawn).
Why this skill exists
Tutorials are universal but easily mis-tuned:
- Too long → players bail before "the actual game" starts
- Too short → players don't learn key verbs; bounce in confusion
- Modal-heavy → players skip-spam through walls of text
- No skip option → veteran players resent re-tutorial on new save
- Hardcoded → impossible to translate / iterate without code
Per ADR 0012, tutorial steps are RULES (not a separate engine system). Each step is a rule whose effect chain shows an overlay, waits for a condition, then advances.
Inputs
- A GDD at
docs/games/<game>/GDD.md - A world plan + level design (knows what the FIRST level looks like; tutorials run there)
- The verb list (movement, primary action, secondary actions)
REQUIRED: Player-perspective objective surface (added 2026-05-08)
Empirical case: merchant 2026-05-08 user feedback — "the scene is much richer, and? i still dont know what should i do?" The game shipped with rich content, beautiful screens, named NPCs, but no answer to "what do I do next?" at any moment. Player saw stats (gold, day, debt) but no actionable instruction.
This is a tutorial-designer responsibility, not a game-designer afterthought. Every tutorial.json must include:
1. A current_objective (or equivalent) state field on the world singleton
Single source of truth for "what should the player be doing right now?" Updated by rules at every key state transition. Always non- empty for the duration of a play session.
2. A HUD binding to surface the objective
Top-center or top-banner is canonical (most visible without overlapping critical HUD). Coordinated with asset-designer to ensure the binding lands.
3. Objective-update rules at EVERY level transition
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.
- 8d ago First seen · 328 lines · 0 tokens per session scan A 18da94d7e8ed
yume-tutorial-designer is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 2,965 once invoked, about $0.0006 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.
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…
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.
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.
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…
character-model
Use when generating a humanoid character ready for animation — player avatar, NPC, enemy, boss, companion. Generates a T-pose reference image, gates an un-rigged preview past the user, then runs the Meshy auto-rig pass and wires the result as a CharacterBody3D (movement) or Node3D (cinematic). Trigger on "make a…
procedural-animation
Use when the user needs runtime-driven bone modification on top of clips — head look-at, foot IK on uneven ground, hand-grabs-prop, additive lean, hit-direction recoil. Code-and-modifier patterns, not generation. Trigger on "look at", "IK", "foot placement", "foot IK", "lean", "additive layer", "feet floating", "hand…