MCPInstall
higgsfield-ai avatar

higgsfield-game-generation

Build and iterate playable browser games, or create game-specific sprites, textures, animated 3D assets, music, SFX, and voice with Higgsfield CLI. Use when: "make a game", "build a browser game", "create game assets", "make a spritesheet", "generate a tileable texture", "animate a 3D game character", or "deploy/publish my game". Supports solo, local multiplayer, and online multiplayer games. NOT for: ordinary image/video generation, game trailers, native mobile/desktop builds, or editing a game without its source files.

Installs
26.6K
Last 24h
—
Trending rank
—
Security
Fail

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/higgsfield-ai/skills --skill higgsfield-game-generation
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads higgsfield-game-generation automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

Security audits

Independent scans of the skill's instructions and bundled files, each dated to when it ran.

Gen Agent Trust Hub PassSAFE ·The skill provides an extensive suite of tools for game development and asset generation. It is authored by higgsfield-ai and correctly utilizes its own vendor-hosted CLI tools and well-known official resources like Blender. No malicious patterns or security risks were detected.· Audited
Socket PassNo alerts· Audited
Snyk FailCRITICAL ·Risk: CRITICAL · 2 issues· Audited

SKILL.md

The instructions your agent reads when the skill is triggered.

Higgsfield Game Generation

Create a coherent, playable web game and deliver the URL, or produce only the requested game assets. Higgsfield CLI owns generation, 3D action discovery, deployment, and optional marketplace publication.

Bootstrap

Before work begins:

  1. If higgsfield is unavailable, install it:
    curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
    
  2. If higgsfield account status reports an expired or missing session, ask the user to run higgsfield auth login, then continue after confirmation.
  3. For a full game, confirm higgsfield game deploy --help works before generating assets. This is the delivery capability check.
  4. Locate this installed skill directory and set it explicitly:
    export GAME_SKILL="/absolute/path/to/higgsfield-game-generation"
    test -f "$GAME_SKILL/scripts/pipeline.py"
    python3 "$GAME_SKILL/scripts/pipeline.py" --help
    
    Never recreate bundled scripts from memory.

Route the request

  • Full playable game — follow the full workflow below.
  • Assets only — read references/stylization.md, then the matching asset reference. Do not deploy a game.
  • Design only — read references/game-design-system.md; return the requested design artifact and asset manifest.
  • Existing game iteration — inspect the supplied source, preserve its architecture and unchanged assets, amend the manifest, rebuild, verify, and redeploy with its existing game ID.
  • Trailer or promotional video — use higgsfield-generate, not this skill.
  • Native mobile/desktop/console runtime — explain that this skill ships browser games; offer a web build unless the user supplied another toolchain.

Full game workflow

1. Plan

Read references/game-design-system.md first and in full. Resolve the game profile, delivery context, core loop, win/lose/restart behavior, performance budgets, input methods, and language handling.

Create design/assets.csv with one row per visual or audio asset:

id,role,type,description,size/ratio,style line ref,source

Read references/multiplayer.md whenever Players is not solo. Local same-screen multiplayer remains client-side; online multiplayer requires the platform server module.

Read references/stylization.md before producing any visual, including procedural canvas art. Derive one STYLE FORMULA and insert it byte-for-byte into every visual prompt. If the brief already fixes the style, state the formula and continue. If several materially different styles fit, show concise options and wait for selection.

No game code or generated visual should exist before the manifest and STYLE FORMULA.

2. Generate assets and build

Start independent generation jobs together, then write the game while those jobs run. Inspect every model contract before first use:

higgsfield model list --json
higgsfield model get <job_type>
higgsfield generate create <job_type> ... --wait --json

Media flags accept local paths or prior upload/job IDs. Keep job JSON in project files when chaining; do not dump IDs into the user-facing reply.

Read the reference matching each manifest row:

AssetRequired reference
Static sprites, backgrounds, UIreferences/stylization.md
Spritesheets / 2D animationreferences/2d-animation.md
Repeating ground, walls, tiles, PBR mapsreferences/textures.md
Any 3D model or animationreferences/3d-animation.md
Music, SFX, voicereferences/audio.md

For 3D animation selection:

higgsfield preset list animation-action --query walk --json
higgsfield preset list animation-action --group Fighting --category Punching --json

When multiple actions fit, show their preview URLs and let the user choose. Pass the chosen integer as --animation_action_id only after checking the target model schema.

Read references/build-game.md last, but before writing game code. Assemble the source ZIP with index.html and exactly one root code module (logic.js or server.js). Use relative asset paths and keep design/assets.csv in the shipped project.

Generation failures get at most two retries. After that, use the best valid result and compensate in code, or amend the manifest honestly.

3. Verify and deliver

Run the local game over HTTP, not file://:

python3 -m http.server 8000

Verify the complete loop, restart, missing assets, console errors, responsive canvas, non-Latin keyboard layout through event.code, touch-only play when mobile is in scope, declared gamepad controls, fixed-timestep behavior, and multiplayer in two sessions when applicable.

Package from the directory that contains the required root files:

zip -r /absolute/path/to/game.zip . -x '*.DS_Store' 'node_modules/*' '.git/*'
higgsfield game deploy /absolute/path/to/game.zip \
  --title "<public title>" \
  --description "<player-facing description>" \
  --thumbnail "<optional https 16:9 image URL>" \
  --favicon "<optional https 1:1 image URL>" \
  --json

For an update, add --game-id <existing_game_id>; never omit it after an update failure, because that would create a different game.

Deployment creates the playable URL. Publishing to the public marketplace is a separate external action and requires explicit user intent:

higgsfield game publish <game_id> \
  --name "<optional listing name>" \
  --description "<optional listing description>" \
  --cover-url "<optional https 16:9 URL>" \
  --logo-url "<optional https 1:1 URL>" \
  --json

Re-open the returned playable URL and repeat the critical smoke path. Deliver the URL returned by CLI; never construct it manually.

Reference order

For full games:

  1. references/game-design-system.md
  2. references/multiplayer.md when Players is not solo
  3. references/stylization.md
  4. Conditional asset references
  5. references/build-game.md

Read each selected reference completely. Do not load unrelated references.

Supporting references opened only when their owning route requires them:

  • references/client-reference.md — online client protocol.
  • references/kernel-reference.md — platform room-kernel contract.
  • references/logic-reference.md — turn-based/event-driven rules module.
  • references/meshy-api.md — raw Meshy fallback only.
  • references/meshy-input-rules.md — mandatory before any image-to-3D submit.
  • references/procedural-animation.md — non-humanoid procedural rigs.

UX rules

  • Mirror the user's language; keep generation prompts in English.
  • User updates are short and describe the game, not internal gates, phase numbers, job IDs, or tool mechanics.
  • Ask only when the answer materially changes the game. Do not batch unrelated questions.
  • Preserve one visual system across generated and procedural assets.
  • Do not request secrets in chat. Raw Meshy fallback may use a user-configured environment key only when the native Higgsfield 3D model is unavailable.
  • Do not publish publicly unless the user requested marketplace publication.

Output

  • Design-only: requested design artifact plus design/assets.csv.
  • Assets-only: usable files/result URLs and their manifest roles.
  • Full game: verified playable URL, a one-line gameplay summary, and marketplace URL only when explicitly published.

FAQ

What does the higgsfield-game-generation skill do?

Build and iterate playable browser games, or create game-specific sprites, textures, animated 3D assets, music, SFX, and voice with Higgsfield CLI. Use when: "make a game", "build a browser game", "create game assets", "make a spritesheet", "generate a tileable texture", "animate a 3D game character", or "deploy/publish my game". Supports solo, local multiplayer, and online multiplayer games. NOT for: ordinary image/video generation, game trailers, native mobile/desktop builds, or editing a game without its source files.

How do I install higgsfield-game-generation?

Run npx skills add https://github.com/higgsfield-ai/skills --skill higgsfield-game-generation in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/higgsfield-game-generation/ (personal) or .claude/skills/higgsfield-game-generation/ (project).

Which AI agents can use higgsfield-game-generation?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is higgsfield-game-generation safe to install?

Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk flagged risks. As with any skill, read the SKILL.md and bundled scripts before installing.

Who maintains higgsfield-game-generation?

It is published by higgsfield-ai in higgsfield-ai/skills. It has 26,583 recorded installs.

More from higgsfield-ai/skills

View all →
higgsfield-ai avatar

higgsfield-generate

higgsfield-ai/skills

Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2.5 for image/design/text, Seedance 2.5 for video, Nano Banana 2 for cartoon characters, Marketing Studio for ads, Seed Audio 1.0 for audio. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "reframe this video", "edit this video from a sketch", "create a 3D model/GLB", "create a sound effect", "make music", "text-to-audio", "create an ad", "make a UGC video", "unboxing", "presenter video", "import product from URL", or "analyze video virality". Supports generic generation, workflows, Marketing Studio, and Virality Predictor. Chain with higgsfield-soul-id for face/identity consistency. NOT for: Soul training, brand systems/brandbooks (use higgsfield-brandkit), photoshoots, cards, YouTube thumbnails (use higgsfield-youtube-thumbnail), explainers (use higgsfield-video-explainer), playable games/assets (use higgsfield-websites), or TTS.

Media & Creative246.2K installs
higgsfield-ai avatar

higgsfield-product-photoshoot

higgsfield-ai/skills

Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gptimage2. Entry point for professional brand/product visuals. Use when: "product photo", "studio shot", "lifestyle image", "Pinterest pin", "hero/banner", "carousel", "ad creative", "Meta ads", "virtual try-on", "model wearing", "person holding product", "closeup with hands", "levitating/floating/splash product", "CGI/surreal product", "restyle", "seasonal/aesthetic variation", or any product, brand, or paid-social creative. Modes: productshot, lifestylescene, closeupproductwithperson, moodboardpin, herobanner, socialcarousel, adcreativepack, virtualmodeltryout, conceptualproduct, restyle. Backend assembles the final prompt; never freehand it. NOT for: no-product text-to-image (use higgsfield-generate), branded avatar video (use higgsfield-generate Marketing Studio), marketplace listing cards (use higgsfield-marketplace-cards), Soul Character training (use hig

Media & Creative223.7K installs
higgsfield-ai avatar

higgsfield-soul-id

higgsfield-ai/skills

Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my Soul", "train my face", "make my digital twin", "build me an avatar", "learn my appearance", "create a character of me", "set up identity for video", "I want my face in generated images". Chain: train Soul (one-time, returns referenceid) → use in higgsfield-generate via --soul-id with models like text2imagesoulv2 or soulcinematic. NOT for: one-shot face swaps (use higgsfield-generate with --image), named-character / non-photo avatars (use higgsfield-generate with prompt).

Media & Creative222.4K installs
higgsfield-ai avatar

higgsfield-marketplace-cards

higgsfield-ai/skills

Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules. Use when the user asks for marketplace listing images, product detail cards, secondary product images, product infographics, lifestyle listing shots, A+ style content, marketplace image sets, or sales-ready product visuals. Backend owns marketplace compliance references and prompt templates; this skill only routes user intent to the CLI. NOT for generic brand product photography without marketplace/listing context (use higgsfield-product-photoshoot), video generation or UGC ads (use higgsfield-generate), or Soul Character training (use higgsfield-soul-id).

Media & Creative220.3K installs
higgsfield-ai avatar

higgsfield-websites

higgsfield-ai/skills

Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (higgsfield website …). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product types, picked via --type on create: website (standalone, no Higgsfield integration — references/website-flow.md), app (Sign in with Higgsfield + fnf SDK, Quanta — references/app-flow.md), game (realtime multiplayer rooms — references/game-flow.md). Routes to the right flow; each carries its own rules and deploy/publish gates. Use when: "build me a website", "make a landing page", "create a web app", "build a SaaS dashboard / portfolio", "make me a game", "deploy this site", "publish". Also owns GAME ART: "make a spritesheet", "tileable texture", "animate a 3D character", game music/SFX — see the game- references. NOT for: single image/video/audio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-market

Media & Creative162.1K installs
higgsfield-ai avatar

higgsfield-video-explainer

higgsfield-ai/skills

Build a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: one narrator, one universal style key, one Seed Audio take and one Gemini Omni clip per block, then server-side assembly with explainervideo. Use when: "make an explainer video", "explain this in a video", "turn this topic or document into a narrated video", "tell this story as an animated video", "make a faceless narrated video", or "show me explainer styles". Supports live CMS presets, custom style references, mascot/faceless modes, two aspects, and optional burned subtitles. NOT for: photoreal films, ads/UGC, talking heads, podcasts, motion typography reels, one-off clips without narration, or editing a finished video.

Media & Creative150.5K installs

Popular media & creative skills

View category →
heygen-com avatar

hyperframes

heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Media & Creative1.5M installs
heygen-com avatar

media-use

heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Media & Creative1.4M installs
heygen-com avatar

hyperframes-registry

heygen-com/hyperframes

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Media & Creative1.3M installs
101-skills avatar

ai-video-generation

101-skills/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

Media & Creative1M installs
101-skills avatar

ai-image-generation

101-skills/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

Media & Creative1M installs
101-skills avatar

ai-avatar-video

101-skills/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

Media & Creative1M installs