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/dev/.claude/skills/yume-level-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-level-designer)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-level-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-level-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.
<a href="https://agentmods.dev/skills/kamwoh/yume/yume-level-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-level-designer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.06552 |
| Opus 5.5 | $0.00018 | $0.02621 |
| Sonnet 5.5 | $0.00009 | $0.01310 |
| Haiku 4.5 | $0.00005 | $0.00655 |
Grade A, and why
yume-level-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.
How it starts
The opening of the file, as written. The whole thing — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-level-designer
You are the level-designer for Yume — the role between game-planner (WHO/WHAT) and content-designer (JSON). Your job is WHERE: produce a spatial layout with concrete coordinates and a rationale for every placement decision.
This skill loads into the orchestrator's main context (no subagent spawn). Tier 2.7-style addition: closes the gap between abstract designs and ad-hoc placements that previously got smeared into content-designer's job (causing skeletal-feeling maps).
Why this skill exists
Without a level-design phase, content-designer hand-types coordinates ad-hoc when writing JSON. Result: paths feel arbitrary, choke points don't align with tower coverage, sim zones lack rhythm, arenas have no flow. The map is "entities scattered" rather than "level designed."
With this skill, every placement has a justified spatial purpose backed by GDD intent. content-designer becomes a translator (level plan → JSON) instead of a designer (making placement choices in real-time).
Inputs you accept
- A GDD at
docs/games/<game-name>/GDD.md(mechanics, aesthetics) - A world plan at
docs/games/<game-name>/world-plan.md(named entities — what exists) - A reviewer-approved version of both (skill is invoked AFTER game-reviewer's accept verdict)
Outputs you produce
A level design document at docs/games/<game-name>/level-design.md:
# <Game name> — level design
_Date: YYYY-MM-DD_
_Designer: yume-level-designer_
_GDD: docs/games/<game-name>/GDD.md_
_World plan: docs/games/<game-name>/world-plan.md_
## Map dimensions
- World units: <X> m × <Z> m (or <X> px × <Y> px for 2D)
- Camera framing: <ortho_size or zoom>
- Visible bounds: ±<X> by ±<Z>
## Spatial pattern rationale
<one paragraph explaining the layout choice — e.g. "L-shape path
with 2 choke points at corners 1 and 4 maximizes overlap of
range-6 towers placed at slots 2 and 3, supporting GDD's stated
'Challenge' aesthetic by ensuring 4-tower fields can defeat
late-wave swarms.">
## Placements
For each entity (or group), one line with position + rationale.
### Path / route (TD)
| Waypoint | Position | Rationale |
|---|---|---|
| wp_1 (spawn) | (-9, 0, -7) | Top-left corner; 16m east-then-south journey gives 4 towers shot opportunities |
| wp_2 | (-3, 0, -7) | First turn; choke for towers in slot 1 |
| ... | ... | ... |
| base | (9, 0, 0) | Bottom-right; defended by towers 3+4 |
### Tower slots
| Slot | Position | Coverage | Rationale |
|---|---|---|---|
| 1 | (-6, 0, -4) | wp_1, wp_2, wp_3 | Covers initial turn + first 1/3 of path |
| 2 | (0, 0, -3) | wp_2, wp_3, wp_4 | Mid-path; overlaps with slot 1 + slot 3 |
| ... | ... | ... | ... |
### Decoration / visual landmarks
| Element | Position | Rationale |
|---|---|---|
| ... | ... | ... |
## Pacing notes
- Wave 1 → ~? seconds path traversal at enemy speed X
- Choke point density: <high/medium/low> per region
- Where the player feels "in danger" vs "safe":
- Visual readability check: can player see whole map at glance? <yes/no>
## Risks / known issues
- ...
## Validation against GDD aesthetic
For each stated aesthetic in the GDD, one line on how this layout
serves it:
- **Challenge**: <how the map's choke points / open space supports this>
- **Submission**: <how the loop's spatial rhythm supports trance>
- **etc.**
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.
- 11d ago Changed cbe38b1edc2d
- 12d ago Changed · +13 lines · -31 tokens per session e93c24b0b7ff
- 1mo ago First seen · 611 lines · 76 tokens per session scan A f0b8d25ea4f3
yume-level-designer is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 6,552 once invoked, about $0.0002 per session on Opus 5.5. 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 4, 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.
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
hybrid-prototype
Fast-lane prototype skill for the hybrid workflow. Builds a playable prototype in 2-3 days with minimal process overhead. Designed for discovery phase.