DangQuangSE/team-development-skills / game-asset-skills/skills/game-asset-prompt
game-asset-prompt
VerifiedGenerate ready-to-paste AI image-gen prompts for 2D game art (character/sprite, icon/UI/item, background/tileset) that stay consistent with the project's art style across separate chat sessions in Claude/Gemini/ChatGPT chat UIs. Use when the user wants to render, generate, or create game art/sprites/icons/backgrounds with AI, or mentions an "art style bible" for a game project. Maintains a persistent `art-style-bible.md` so style doesn't drift between requests, and gives a post-generation checklist plus post-processing guidance for common technical misses (transparency, size, aspect ratio).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.0 KB |
| references/background-tileset-template.md | markdown | 2.2 KB |
| references/bible-bootstrap-questions.md | markdown | 3.6 KB |
| references/bible-field-names.md | markdown | 1.5 KB |
| references/character-sprite-template.md | markdown | 2.6 KB |
| references/icon-ui-item-template.md | markdown | 2.1 KB |
| references/post-generation-checklist.md | markdown | 2.1 KB |
| references/post-processing-guide.md | markdown | 3.3 KB |
references/character-sprite-template.md
View on GitHub# Character/Sprite Prompt Template
For any single-subject animated or posed sprite: character, creature, vehicle, ship — anything that needs one or more consistent frames/poses.
## Gather before generating
- Subject name/description (what it is, if not obvious from context)
- Pose/frame list: which frames are needed (e.g. idle, walk, attack — or for a vehicle: default, banking-left, banking-right, destroyed)
- Any per-subject identifying details that must stay identical across every frame in the set (colors, markings, silhouette, proportions)
If a reference image exists (bible-level `[REFERENCE_IMAGE_PATH]` or a per-asset image the user just provided), skip asking for a text description of appearance — tell the user to attach the image alongside the prompt below instead.
## Prompt anatomy (6-part, fill every slot)
```text
Job: Generate a single [pose/frame name] game sprite, isolated subject, no scene.
Subject: [subject name/description — identifying details repeated verbatim across every frame's prompt in the same set].
Medium/Style: [STYLE_ANCHOR_PHRASE], line weight [LINE_WEIGHT].
Lighting: flat/even lighting consistent with [ART_DIRECTION], no dramatic shadow unless the art direction calls for it.
Framing: [VIEW_ANGLE] — camera-facing, not a side or three-quarter flyby angle unless [VIEW_ANGLE] explicitly says otherwise. Full subject in frame, centered.
Mood/Palette: render the subject using only these colors as actual surface color ([PALETTE_HEX]) — do not display the hex codes, a color chart, swatch strip, or legend anywhere in the image; colors appear only on the subject itself.
Technical spec: [DEFAULT_RESOLUTION — sprite value], isolated subject on flat white or black background, no gradient, no shadow (chat tool can't guarantee true alpha — see post-processing guide after generation).
Negative constraints: no watermark, no text/logos, no crop of the main subject, no style drift from the described art direction, no background scene elements, no additional subjects in frame, no color palette/swatch/chart/legend anywhere in the image.
```
If generating multiple frames/poses for the same subject in one session: paste `[STYLE_ANCHOR_PHRASE]` once at the start of the chat session instead of repeating the full style description in every single frame's prompt — keep repeating the Subject's identifying details every time, though, since that's what keeps the character/vehicle itself consistent across frames.
## After sending
Continue to the post-generation checklist and, if a technical spec is missed, the post-processing guide (`references/post-generation-checklist.md`, `references/post-processing-guide.md`).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |