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-screen-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-screen-author)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-screen-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-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-screen-author"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-screen-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 | $0.00051 | $0.03695 |
| Opus 5.5 | $0.00020 | $0.01478 |
| Sonnet 5.5 | $0.00010 | $0.00739 |
| Haiku 4.5 | $0.00005 | $0.00369 |
Grade A, and why
yume-screen-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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-screen-author
STABLE — 2D fit-fit pipeline (confirmed 2026-05-24). This skill
- its harness (compose_screen, wireframe_to_screen) 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
screens.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 screen author for Yume. You read a wireframe image of a
modal or full-cover UI and produce a fit-fit screen entry for that
game's screens.json — meaning the in-game screen matches the
wireframe pixel-for-pixel (modulo the wireframe→viewport scale) AND
its interactive elements wire correctly.
This is the sibling skill to yume-hud-author. Same harness pattern,
broader vocabulary, extra validation. The deterministic surface lives
at tools/visual_layout/wireframe_to_screen.py.
Why this skill exists (vs yume-hud-author)
- HUD = always-on overlay during gameplay. Read-only display (vitals, minimap, objective, hotbar). Narrow element catalog: 6 types, all non-interactive.
- Screen = modal or full-cover UI gated by player input
(inventory open with
I, pause withEsc, settings menu, title). Broader catalog: 13 types includingbutton,slider,checkbox,option_button— interactive elements with effect chains.
Screens are the bigger semantic surface. A button click can fire any effect type the engine supports (state_set, transition_screen, emit, play_sound, ...). The skill's job is to wire those chains correctly WITHOUT inventing actions outside what the manifest allows.
When to invoke
- A
compose_screen.pyrun that needs to convert a wireframe → screen entry (the normal authoring path) - Iterating on an existing screen — re-runs replace the entry
identified by
screen_id - New screen — first time a game adds e.g. an inventory or pause UI
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 Changed · +4 lines · -119 tokens per session 14f684951a8a
- 1mo ago First seen · 365 lines · 170 tokens per session scan A 96a4f6c6b09f
yume-screen-author is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 3,695 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.