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-hud-author/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-hud-author)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-hud-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-hud-author/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-hud-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-hud-author.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 | $0.00126 | $0.03462 |
| Opus 5 | $0.00063 | $0.01731 |
| Sonnet 5 | $0.00025 | $0.00692 |
| Haiku 4.5 | $0.00013 | $0.00346 |
Grade A, and why
yume-hud-author 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 12d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-hud-author
STABLE — 2D fit-fit pipeline (confirmed 2026-05-24). This skill
- its harness (compose_hud, wireframe_to_hud) is locked. Modifying the workflow requires an ADR + scenario regression tests. Active work on Yume's 3D map/world pipeline lives at
/yume-map-authorand is NOT bound by this status.Note: the live
hud.jsonper-game CONTENT can keep evolving. Stable means "the harness produces JSON correctly." Per-game UX iteration is normal authoring, not a harness change.
You are the HUD author for Yume. You read a wireframe image and
produce a fit-fit hud.json — meaning the in-game HUD matches the
wireframe pixel-for-pixel (modulo the wireframe→viewport scale).
This skill is the LLM-in-the-loop layer of the wireframe-to-hud
harness. The deterministic surface (preprocess + postprocess) lives
at tools/visual_layout/wireframe_to_hud.py. The wisdom that turns
a wireframe into HUD JSON lives here.
Why this skill exists (and what it replaces)
The earlier yume-hud-layout skill used opencv k-means to parse
wireframes. It worked for clean wireframes but failed on Gemini's
output variance: subtle color drift between regions, soft edges from
JPEG compression, regions that looked obviously-vitals to a human but
quantized into the wrong cluster.
The fix isn't a smarter parser. It's putting Claude at the parsing step. Claude reads the wireframe directly via vision, knows the schema, and produces the JSON without intermediate parsing. The CV gives us reliable image dimensions; the LLM gives us reliable semantic identification.
Fit-fit means: what's drawn IS the layout. No "preserve existing panel sizes" merge step. No "pick reasonable defaults" templates. The wireframe is the source of truth.
When to invoke
- A
compose_hud.pyrun that needs to convert a new wireframe → hud.json (the normal authoring path) - Iterating on an existing wireframe — re-runs produce a fresh hud.json that matches the new wireframe
- New game scaffold — first HUD ever
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.
- 12d ago First seen · 310 lines · 126 tokens per session scan A d50be0669eaf
yume-hud-author is a skill published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 126 tokens to every session and 3,462 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…
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".
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".