threejs-image-generator
Generate and edit 2D image assets for Three.js games using Google's Gemini image API. Use for concept sheets, image-to-3D inputs, texture references, sky/background plates, decals, logos, icons, GUI art, title/menu art, thumbnails, marketing stills, and source images that feed threejs-3d-generator. Also use for direct image editing when the user provides an image path.
Works with
--- name: threejs-image-generator description: Generate and edit 2D image assets for Three.js games using Google's Gemini image API. Use for concept sheets, image-to-3D inputs, texture references, sky/background plates, decals, logos, icons, GUI art, title/menu art, thumbnails, marketing stills, and source images that feed threejs-3d-generator. Also use for direct image editing when the user provides an image path. license: MIT --- # Three.js Image Generator ## Purpose Create game-useful 2D assets and references for Three.js projects. This skill is the image-generation layer for the Three.js game system: it produces concepts, textures, decals, UI art, and 2D inputs that can be handed to `threejs-3d-generator` for image-to-3D model creation. Provider: Google's Gemini image API. Resolve `<this-skill-dir>` in the commands below in this order: `~/.claude/skills/threejs-image-generator`, `~/.codex/skills/threejs-image-generator`, `~/.agents/skills/threejs-image-generator`, or repo `skills/threejs-image-generator`. ## When To Use Use this skill before procedural-only fallback when a Three.js game needs: - 2D-to-3D reference images for `threejs-3d-generator`: characters, creatures, buildings, ships, cars, weapons, props, pickups, terrain modules. - Texture and material references: terrain, road, rock, sand, metal, sci-fi panels, trim sheets, decals, hazard labels, signs. - Environment images: skies, backdrops, city horizons, nebula plates, menu backgrounds, parallax layers. - UI art: logos, faction marks, icons, item cards, ability badges, cockpit decals, GUI panels, title art. - Existing-image edits, style variants, cleanup, palette alignment, or concept sheet refinements. For premium/AAA/showcase graphics work, generate at least one relevant image for high-value 2D surfaces or image-to-3D inputs unless the credential probe or a real generation attempt shows a blocker. ## API Key Never store API keys in skill files or browser/game code, and never paste a key value into a report. The script reads `--api-key` or `GEMINI_API_KEY`. Step 0, before declaring the key unavailable: run this skill's own probe and paste its literal output into the report. ```bash uv run <this-skill-dir>/scripts/generate_image.py probe # prints GEMINI_API_KEY=SET|MISSING ``` `GEMINI_API_KEY=MISSING` is only a valid skip/blocker reason when this output is shown. Keys defined only in a shell profile can be absent from the process env; if the plain probe prints MISSING unexpectedly, wrap it: `zsh -lc 'source ~/.zprofile 2>/dev/null || true; source ~/.zshrc 2>/dev/null || true; uv run <this-skill-dir>/scripts/generate_image.py probe'`. When the director skill is loaded, prefer `threejs-game-director/scripts/probe_asset_credentials.sh`, which probes all three asset keys at once. ## Tool Script Run from the user's current project directory so output lands in the game project: ```bash uv run <this-skill-dir>/scripts/generate_image.py --prompt "your image description" --filename assets/concepts/output.png --resolution 2K ``` Edit an existing image: ```bash uv run <this-skill-dir>/scripts/generate_image.py \ --input-image assets/concepts/ship.png \ --prompt "turn this into a battle-worn red racing livery with clearer material zones" \ --filename assets/concepts/ship-red-livery.png \ --resolution 2K ``` Resolution mapping: - `1K`: quick concepts, icons, draft sheets. - `2K`: default production reference for image-to-3D, textures, backgrounds, UI panels. This is also the script default when `--resolution` is omitted. - `4K`: hero splash/title art, high-detail texture references, large sky/background plates. ## Prompt Patterns Image-to-3D reference: ```text Create a clean 3D-generation reference image of [asset]. Centered single object, full object visible, plain light background, readable silhouette, clear material zones, game-ready [genre/style], no motion blur, no cropped parts, no text. ``` Riggable character/creature reference: ```text Create a full-body [T-pose/A-pose/side-view creature] reference for 3D rigging: [details]. Symmetric stance, visible hands/feet/limbs, plain background, readable costume/anatomy layers, no weapon fused to hands. ``` Texture/material reference: ```text Create a seamless game texture reference for [surface]. Orthographic/top-down, PBR-friendly albedo, clear material variation, no perspective, no baked strong shadows, [style/material details]. ``` Logo/icon/UI art: ```text Create a crisp game UI [logo/icon/badge/panel] for [faction/item/ability]. Transparent-friendly silhouette, high contrast at small size, [genre styling], no tiny unreadable text. ``` Sky/background: ```text Create a wide game background plate of [environment]. Layered depth, readable horizon, [time/weather/style], suitable behind a real-time Three.js scene, no foreground subject. ``` ## Three.js Integration Rules - Save concepts and image-to-3D sources under `assets/concepts/`. - Save textures, decals, icons, and GUI source images under `assets/textures/`, `assets/decals/`, or `assets/ui/`. - For image-to-3D, hand the saved image path to `threejs-3d-generator` and record the chain in the external asset ledger. - Do not call the image API from client-side game code. - Convert generated PNGs into runtime formats deliberately: PNG for alpha/UI, JPG/WebP/KTX2 for larger opaque textures where the project pipeline supports it. - Verify how the image appears in game, not only that the file exists. ## Required Report Report: - Credential probe output or command blocker. - Prompt and purpose. - Output path. - Resolution. - Whether the image was used directly, edited further, or handed to `threejs-3d-generator`. - Any remaining integration work such as compression, UV assignment, alpha cleanup, or atlas packing. Do not mark a premium graphics phase complete if the needed image outputs are missing and the only justification is "procedural is enough" for high-value UI, texture, sky, decal, logo, or image-to-3D surfaces.
More SEO & Marketing skills
ai-video-generation
skills-101/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
skills-101/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
ai-avatar-video
skills-101/superpowers
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

