- Home
- Skills
- Game Development
- Game UI & UX Cleanup — Kill Game Slop
More screenshots
Works with the AI Agents you already use
Game UI & UX Cleanup — Kill Game Slop
An engine-agnostic AI agent skill for clearer game UI, copy, visual effects, and audio while preserving art direction.
$5
Game UI & UX Cleanup — Kill Game Slop
Example session with this skill installed
$kill-game-slop Review this text-only fantasy game mockup without editing code. Facts: after clicking a move, the UI immediately says Choice locked; the server can later accept or reject it; an accepted choice may be changed until the timer closes; rejection preserves the previous selection. The decorative header is Destiny awaits. Suggest accurate state messages and verification checks. Preserve the fantasy theme and gameplay rules. No screenshots or running game are available.
- Read your context and instructions
- Compiled the game ui
Text-only presentation review
Based on the supplied state rules, Choice locked promises a final state too early. Sending a request, receiving server acceptance, and final locking need distinct messages. The fantasy header can stay: the supplied text establishes no readability problem with its styling.
| State | Suggested message | Meaning |
|---|---|---|
| Before selection | Choose your move | Invites the action without implying a result. |
| Request sent, awaiting reply | Sending choice... | Shows that server acceptance is pending. |
| Server accepts, timer open | Choice received. You can change it before the timer ends. | Acknowledges acceptance and the remaining option to change. |
| Server confirms final lock | Choice locked | Uses the final label only after authoritative confirmation. |
| Server rejects | Choice not accepted. Your previous choice is still selected. | Reports failure without falsely replacing the prior selection. |
Keep the existing fantasy art, rules, timing window, and server validation. Use the existing localization and UI state resources if these changes are implemented. Preserve non-color cues for pending, accepted, rejected, and locked states.
Checks to run in the actual game: delay the server response; reject a changed selection; change an accepted choice before closing; check the final server-confirmed lock; leave and re-enter the scene; inspect long localized text and the target input method.
Verification performed: compared the proposed text with the state rules provided in the prompt. This is an illustrative mockup review. No code was edited and no layout, animation, audio, or runtime behavior was verified.
Connects securely to your tools. The creator never sees your data.
About this skill
Kill Game Slop helps AI coding agents review and improve generic, cluttered, redundant, or misleading game presentation. Use it for HUDs, menus, tutorial copy, visual effects that obscure play, and repeated audio cues that mask useful information.
What it does
- Finds concrete player friction before recommending a change.
- Clarifies UI hierarchy and messages about selected, sent, accepted, or locked states.
- Reduces competing visual and audio effects while preserving intentional impact and celebration.
- Traces shared resources and checks the affected flow, viewport, input method, and localized text.
- Preserves art direction, accessibility cues, gameplay rules, and purchase or server-validation semantics.
What is included
A portable SKILL.md workflow, three reference documents with checks and illustrative examples, installation instructions, and the original MIT license. Engine-specific notes cover Unity, Unreal, Godot, Roblox, and web/custom runtimes. These are review workflows, not tested engine integrations. No scanner, AI detector, executable tool, or additional runtime dependency is included.
Public source and paid package
The core project remains freely available under the MIT License at https://github.com/Ddrubok/kill-game-slop. This $5 one-time listing provides an installation-ready package of that public material. Purchase does not grant exclusive access to the source.
Gallery images are AI-generated illustrations of the workflow, not captured game sessions.
Review quality depends on the supplied project, captures, and available runtime or editor access. Text and source inspection alone cannot verify visual quality, animation, or audio. Opaque binary assets require the appropriate editor; otherwise the skill provides a precise edit specification. Engine notes are workflows, not tested integrations. Gameplay balance and economy changes are outside its scope.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
Reads the game project and linked reference documents. For requested fixes, writes only files relevant to the agreed flow and uses the project's normal checks. Terminal, browser, and editor access depend on the project and task. No connected third-party account, environment variable, or network service is required by this Markdown package. GitHub links are optional source and attribution references.