Loading...
Loading...
AI agent skills for image and video generation via Higgsfield AI. Use this skill when asked to generate images or videos from a prompt, create branded ad video (UGC, unboxing, TV spot) with Marketing Studio, produce product photography or marketplace cards, train a reusable face identity (Soul Character), score a finished video's virality, or build/edit/deploy a full-stack website. Image/video generation spans 30+ models (Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, GPT Image 2, …). Bundles five skills: higgsfield-generate, higgsfield-soul-id, higgsfield-product-photoshoot, higgsfield-marketplace-cards, and higgsfield-websites Markdown-based agents.
npx skill4agent add starchild-ai-agent/official-skills higgsfieldnpx skillsnpx skills add higgsfield-ai/skillsgit clone --depth 1 https://github.com/higgsfield-ai/skills.git
cd skills
./setup| Skill | Invoke | Description |
|---|---|---|
| | Image, video, 3D, and audio generation across 30+ models (Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Seed Audio 1.0, Flux 2, GPT Image 2, …), plus Marketing Studio for branded ads with avatars/products/hooks/settings and Virality Predictor scoring for finished videos. |
| | Train a Soul Character — a reusable, face-faithful identity model. Returns a |
| | Brand-quality product imagery with mode-specific prompt enhancement. 10 modes (studio, lifestyle, Pinterest, hero banner, ad packs, virtual try-on, …) backed by |
| | Marketplace product cards: compliant main image, secondary product images, and A+ style modules via backend prompt enhancement. |
| | Build, edit, and deploy full-stack websites — React 19 + TanStack Start, server-rendered as one Cloudflare Worker with D1 / R2 / KV / Durable Objects / Containers. Create → get git repo access → edit locally → push → deploy preview/production, all via |
generateproduct-photoshootmarketplace-cardswebsitesgeneratehiggsfield-product-photoshoot| Mode | What it's for |
|---|---|
| Product on neutral / studio / catalog background |
| Product in a real environment — hands, action, atmosphere |
| Tight crop with hands or partial face — beauty, demonstrating |
| Vertical 2:3 Pinterest-native pin, moodboard feel |
| Wide-format website / email / campaign header |
| 3–10 connected slides for IG / LinkedIn / Facebook |
| Coordinated pack of static ad variants for Meta / TikTok / Pinterest / Google |
| Product worn or used by an AI-rendered model |
| Surreal / CGI-style / levitating / splash / sculptural product |
| Transform an existing image's aesthetic, mood, or seasonal context |
higgsfield-generate| Mode | What it's for |
|---|---|
| Default. Casual, organic-feel content from a presenter |
| Tutorial / explainer |
| Unboxing reveal |
| Clean product highlight, polished |
| Presenter giving an opinion |
| Broadcast-style commercial |
| Experimental, model picks the vibe |
| Trying on clothing — UGC vibe |
| Trying on clothing — polished, model-driven |
| What you want | Skill | Note |
|---|---|---|
| Generate any image / video from a prompt | | Prefers |
| Generate audio from a prompt | | Prefers |
| Image with my own face | | One-time training, then |
| Branded product photo (studio / lifestyle / Pinterest / hero / ad pack) | | Mode-specific prompt enhancer + |
| Marketplace product cards / A+ style content | | Main image, secondary images, and A+ style modules with hidden marketplace prompt templates |
| Branded ad video / UGC / unboxing / TV spot | | Marketing Studio mode with avatars + products + optional hooks/settings |
| Analyze a video's hook / attention / virality potential | | Uses Virality Predictor ( |
| Train a custom face identity | | 5–20 photos, returns |
| Image-to-video animation | | Prefer |
| Build / edit / deploy a website, web app, landing page, or dashboard | | Full-stack React 19 + TanStack Start on Cloudflare; |