# AI use cases for Skills (higgsfield-ai/skills)

Repo: [higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) | Use cases: 3 | Page: https://dedupedai.com/use-cases/higgsfield-ai-skills/

Higgsfield AI Skills is a set of agent skills for image and video generation and complete visual brand systems via Higgsfield AI, including Marketing Studio and Virality Predictor video scoring. It works with Claude Code, Cursor, Codex, and other AI coding agents that load Markdown-based skills.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Add image and video generation to your coding agent: https://dedupedai.com/use-cases/higgsfield-ai-skills/install-higgsfield-skills-in-your-agent/
- Create branded product photos from your agent: https://dedupedai.com/use-cases/higgsfield-ai-skills/make-product-photos-with-higgsfield-skills/
- Generate a complete brand kit and brandbook: https://dedupedai.com/use-cases/higgsfield-ai-skills/build-a-brand-kit-with-higgsfield-skills/

## How to add image and video generation to your coding agent with Skills

Repo: [higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Install the Higgsfield Skills with one command and generate images or video from a prompt.

**Who it is for:** A developer using Claude Code or Cursor who wants visuals for a project without switching tools.

**The problem:** Coding agents write code well but have no built-in way to generate images, video or audio.

**The outcome:** Your agent can call the higgsfield-generate skill to make images, video, 3D and audio from a prompt.

### Steps

1. Run `npx skills add higgsfield-ai/skills` (the recommended cross-agent install)
2. Let the skill setup install the Higgsfield CLI and sign in
3. Ask your agent to use the higgsfield-generate skill with your prompt
4. For image to video, the README suggests `seedance_2_5` with `--mode omni_reference --start-image`

### Prompt to paste into your agent

```text
Install higgsfield-ai/skills with `npx skills add higgsfield-ai/skills`, then use the higgsfield-generate skill to make <image or video> of <subject>. Show me the result before generating variations.
```

### Caveat

Generation runs through Higgsfield AI, so an account is needed and usage may be billed by them.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/higgsfield-ai-skills/install-higgsfield-skills-in-your-agent/

## How to create branded product photos from your agent with Skills

Repo: [higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README

Use the product photoshoot skill for studio shots, lifestyle scenes, hero banners and ad packs.

**Who it is for:** A small shop owner or marketer who needs consistent product imagery fast.

**The problem:** Product photography is slow and costly, and every channel wants a different format.

**The outcome:** Product imagery in one of 10 modes, from studio shots to social carousels and ad packs.

### Steps

1. Install the Skills with `npx skills add higgsfield-ai/skills`
2. Invoke the higgsfield-product-photoshoot skill and give it your product image
3. Pick a mode such as `product_shot`, `lifestyle_scene`, `hero_banner` or `ad_creative_pack`
4. Review the outputs and ask for a `restyle` if you want a different mood or season

### Prompt to paste into your agent

```text
Use the higgsfield-product-photoshoot skill on <product image>. Make a product_shot and a hero_banner, then an ad_creative_pack for Meta. Show me each before moving on.
```

### Caveat



Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/higgsfield-ai-skills/make-product-photos-with-higgsfield-skills/

## How to generate a complete brand kit and brandbook with Skills

Repo: [higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Let the brandkit skill produce palettes, SVG logo marks, typography, mockups and a brandbook.

**Who it is for:** A founder launching a project who needs a visual identity before the site goes live.

**The problem:** A consistent identity normally needs a designer and several rounds of revisions.

**The outcome:** A visual identity with editable SVG logo marks, approved palette and type, and PPTX or PDF brandbooks.

### Steps

1. Install the Skills with `npx skills add higgsfield-ai/skills`
2. Invoke the higgsfield-brandkit skill and describe your project and audience
3. Approve the palette and typography when the skill asks
4. Request mockups, social graphics or a canonical brandbook once the base is approved

### Prompt to paste into your agent

```text
Use the higgsfield-brandkit skill to create a visual identity for <project>. Pause for my approval on palette and type, then export the logo as SVG and a PDF brandbook.
```

### Caveat

The skill is approval-aware, so expect it to stop and ask before moving between stages.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/higgsfield-ai-skills/build-a-brand-kit-with-higgsfield-skills/
