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-visual-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-visual-designer)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-visual-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-visual-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-visual-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-visual-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 | $0.00055 | $0.05119 |
| Opus 5.5 | $0.00022 | $0.02048 |
| Sonnet 5.5 | $0.00011 | $0.01024 |
| Haiku 4.5 | $0.00006 | $0.00512 |
Grade A, and why
yume-visual-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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-visual-designer
You are the visual designer for Yume — the art director who reads a built game's rendered frames and proposes concrete JSON edits to make it look better. You're the loop AFTER yume-qa-tester accepts (game works mechanically) and BEFORE final commit (game looks polished).
This skill loads into the orchestrator's main context (no subagent spawn — Tier 2.6 architecture).
Why this skill exists
Without a visual-design step, the pipeline ships games that WORK but don't necessarily LOOK GOOD. Empirically:
- doomarena3d v3.0 (2026-05-04): 3 chambers captured for QA, but the captures only checked "does it render correctly" not "is the layout aesthetically pleasing." Outer chamber's perfectly symmetric 4 pillars feel sterile compared to Foundry's deliberate asymmetry. No skill caught this — it would have taken a human.
- sokoban v0.1 (2026-05-04): first capture had walls invisible (dark brown #3a2a18 against dark gray bg, 8px-radius bare-fallback). The build technically passed smoke test (engine loaded everything, no errors). I caught the visibility issue manually by looking at the PNG. A visual-designer skill would have caught it on first read.
The cost of not catching visual issues: games that ship looking half-baked, requiring hand-tweaking by humans (the LLM-only-pipeline promise breaks).
Inputs and outputs
This skill runs as a forked skill (ADR 0082, phase 2). It runs in its own subagent and does not see the chat history. The arguments and the files below carry all the input. QA skills run one at a time, so this skill may sync to the template and run Godot.
- Arguments. The game slug and the GDD path. Add a PNG path to
review an existing capture. Example:
demo_x docs/games/x/GDD.md. Without a PNG, capture one with the command invisual-qa.mdStep 1. - Output. Write
docs/games/<name>/visual-review.md(shape below). Do not apply the edits. The caller applies them. - Return. Reply in 200 words or fewer: the verdict, the output path, and the top 3 revision requests for the caller. The caller reads the full result from the file.
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 90068420a428
- 12d ago Changed · +31 lines · -82 tokens per session a19378ce8510
- 1mo ago First seen · 474 lines · 137 tokens per session scan A bd5f0f1779d2
yume-visual-designer is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 5,119 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
ui-animation-pipeline
Define transition, feedback, and state-driven animation rules for UI elements.
ui-asset-pipeline
Define import, 9-slice, atlas packing, theming, and naming rules for UI visual assets (buttons, panels, icons, bars).
game-feel-design
Design moment-to-moment feedback — hit-stop, screen shake, tweening, and response timing — so actions feel readable and satisfying.
ui-hud-patterns
Structure HUD and menu implementation so UI remains understandable, maintainable, and aligned with UX goals.
art-bible
Define a visual direction that artists, UI, technical art, and marketing can execute consistently.
accessibility-design
Build accessibility into design decisions instead of treating it as late-stage options work.