Yuki001

Execute image generation, editing, and chroma-key transparent-background workflows with GPT Image 2 / gpt-image-2 through the bundled scripts. Use when GPT Image is the selected backend and a supplied prompt or edit instruction must be executed for text-to-image generation, reference-image editing, multi-reference editing, masked inpainting, or chroma-key background removal. Treat the supplied prompt as authoritative; this skill does not search prompt galleries, choose art direction, or perform general prompt planning.

READ this skill when designing or planning any game system architecture — including combat, skills, AI, UI, multiplayer, narrative, or scene systems. Contains paradigm selection guides (DDD / Data-Driven / Prototype), system-specific design references, and mixing strategies. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.

Comprehensive ImageMagick 7 command-line image processing for inspecting, converting, resizing, cropping, compositing, masking, drawing, annotating, color correction, quantization, filtering, morphology, distortion, animation, montage, comparison, metadata, batch automation, and advanced pixel analysis. Use whenever a task mentions ImageMagick, `magick`, `identify`, `mogrify`, raster image conversion or batch image manipulation, or when a reproducible CLI pipeline is preferable to a GUI or language binding. Also use for debugging ImageMagick commands, porting ImageMagick 6 `convert` syntax to version 7, choosing coder/delegate options, and safely processing untrusted or large images. Do not use merely to edit an existing SVG as vector source or when the user explicitly requests a different image tool.

READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap, emission, dissolve, hatching, or any stylized rendering effect. Contains preset styles and feature-to-reference mappings for lilToon, Poiyomi, UTS2, RToon, SToon, and ToonShadingCollection. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.

Review, critique, compare, improve, or stress-test an existing game concept, GDD, mechanic, puzzle, economy, level, theme, emotional arc, interface, narrative, social feature, prototype, pitch, or playtest result. Use when the user asks what is weak, risky, unclear, unbalanced, contradictory, insufficiently engaging, or worth validating next in a game design. Produce evidence-based findings, explicit tradeoffs, and the smallest useful prototype or playtest experiment.

Extract ordered still-image frames from local video files with FFmpeg, using a fixed FPS, an exact frame count, explicit timestamps, or every source frame; optionally remove a flat chroma-key background and emit timing metadata. Use for video-to-frame conversion, animation frame sampling, contact-sheet inputs, sprite animation source frames, dataset frames, thumbnail sequences, or any request to split MP4, WebM, MOV, MKV, AVI, or other FFmpeg-readable video into PNG, WebP, or JPEG images.

Develop game story and narrative through one-question-at-a-time writer interviews. Produces narrative docs under gat/narrative/ or runs as discussion-only. Use when the user wants story, plot, lore, worldbuilding, characters, quests, dialogue, narrative tone, or authored story content for a GAT game.

Specialized in game numerical design, this skill designs first-pass game balance values, diagnoses and tunes existing systems, and evaluates balance proposals by building and running executable models, simulators, parameter sweeps, and evidence checks. Use for combat, progression, economies, items/builds, PvP/metagames, and random rewards when the task requires concrete numbers or a supported verdict. Do not use for broad qualitative game-design critique without a numeric or systemic balance decision.

Design one system within a specific milestone's scope: write the milestone-scoped system GDD, content data, and system art doc, and update the milestone brief's progress. Requires a mandatory milestone argument.

Remove image backgrounds locally with Lucida's bgr CLI and save transparent RGBA PNGs while preserving soft alpha in glass, smoke, glow and VFX, camouflage, text and logos, line art, illustrations, and print designs. Use when a user asks to remove, erase, isolate, cut out, or make the background of an image transparent; prefer Lucida for translucent or effect-heavy artwork and BiRefNet-HR for high-resolution solid physical objects or product photos.

Plan milestone slices from overview + narrative alone (no system GDDs required), create per-milestone directory skeletons and briefs, and write gat/milestone/milestone.md. Runs before per-system design. Stops before technical design, task breakdown, or implementation.

Generate images through OpenRouter's dedicated Image API. Use this skill whenever the user wants to create, render, generate, or save images with OpenRouter, including text-to-image, image-to-image/reference images, choosing OpenRouter image models, listing image models, setting resolution/aspect ratio/quality/output format, or passing provider-specific image options. Prefer the bundled Python script so API options are passed explicitly as command-line arguments instead of hand-written ad hoc curl requests.

Generate and download videos through OpenRouter's dedicated asynchronous Video API. Use this skill whenever the user wants to create, render, generate, poll, resume, or save an OpenRouter video, including text-to-video, first/last-frame image-to-video, reference-to-video, choosing or listing video models, setting duration/resolution/aspect ratio/audio/seed, checking job status, downloading completed outputs, configuring callbacks, or passing provider-specific video options. Prefer the bundled Python script so asynchronous jobs and API options are handled consistently.

Brainstorm a game idea through one-question-at-a-time designer interviews. Produces game.md, systems-index.md, and art-direction.md, or runs as discussion-only.

Plan, generate, inspect, vision-evaluate, refine, and package images and visual assets for game development through a backend-agnostic production loop. Use for PNG or SVG props, icons, characters, environments, tiles, UI, HUD/gameplay screens, VFX, transparent cutouts, concept or worldbuilding boards, sprite sheets, static sprite collections, or animation frames; especially when the task needs batch generation, native prompts or ComfyUI/Stable Diffusion Danbooru tags, reference consistency, background removal, format validation, or iterative quality scoring. This skill orchestrates available image, image-edit, vision, SVG, MCP, local, and host-native tools without requiring a specific generator.

Generate procedural 3D models from natural-language requests by writing a constrained buildModel(ctx) module that uses Three.js, bundled builders and helpers, deterministic validation and export scripts, PNG previews, and optional browser visual review. Use when needs to create, revise, export, or visually audit programmatic 3D assets in GLB, glTF, OBJ, or STL without Blender or another DCC tool.

Inspect the repo state and show a status panel across all milestones, recommending the earliest actionable next step in the workflow.