token-holdem

Generate final visual image assets for Token Hold'em and save them as real repo files under assets/. Use when Codex is asked to generate actual image files, create tavern background art, create LLM avatar portraits, create poker table assets, create transparent PNG/WebP sprites, use image generation to create assets, save generated assets into the repo, update the asset manifest, integrate generated art through CSS/HTML/token_holdem/render.py, or replace CSS placeholders with real art assets. This skill must produce actual generated files when image generation is available, not just prompts.

Turn Gradio apps into full-page, immersive, game-like scenes using custom HTML, CSS, and layered layout architecture. Use when Codex is asked for full-page game UI, immersive Gradio layout, replacing generic Gradio panels, background scene composition, HUD/sidebar/action bar layout, CSS layering, z-index strategy, responsive game scene design, or Token Hold'em tavern poker scene composition.

Review and improve Token Hold'em final UI polish, UX quality, game feel, animations, hover/focus states, readability, accessibility, responsive behavior, and premium cozy tavern presentation. Use when Codex is asked for UI polish, UX review, game feel, animations, hover states, readability, accessibility, final quality pass, polish punch list, prioritized improvements, mobile checks, or a premium feel review for the Token Hold'em app.

Build Gradio web UIs and demos in Python. Use when creating, modifying, debugging, or answering questions about Gradio and its capabilties, components, event listeners, or layouts.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.

Manage Token Hold'em image asset generation, organization, manifests, naming, and UI integration. Use when Codex is asked to generate image assets, background assets, tavern or poker table art, candle/bar/bartender/chip/card assets, transparent PNGs, asset naming rules, asset manifests, or integrating generated images into the Token Hold'em UI.

Design Token Hold'em AI model poker avatars as readable tavern characters inspired by model personalities rather than exact company logos. Use when Codex needs avatar concepts, LLM character designs, poker personas, professor/maverick/villain/etc. variants, sprite prompts, portrait prompts, image generation prompts, transparent asset requirements, expression or emote states, naming conventions, or consistency checklists for AI player avatars.

Define and maintain the visual art direction for Token Hold'em, a cozy pixel-art tavern poker game. Use when Codex is asked for tavern atmosphere, pixel art direction, background or environment prompts, lighting, palette, mood, camera angle, visual consistency, style bibles, image generation prompts, negative prompts, visual QA, or premium game-ready tavern poker scene guidance. Do not use to generate final background art until gameplay layout constraints are known.

Design and implement the actual Token Hold'em poker table UI/UX layout. Use when Codex is asked for seat positioning, an 8-player poker table layout, dealer button movement, community cards, player stack display, pot display, action indicators, responsive poker UI, readable table zones, card placement rules, or implementation checklists for the Token Hold'em table.