# EvoLink Agent Skills for Creative Generation

Demand-led skills for agents that create ad images, product visuals, image edits, and short videos through EvoLink.

The first batch uses scene and intent words as public skill slugs. Seedance 2 and GPT Image 2 are the execution models inside each workflow, not the primary distribution labels.

Seedance 2.5 early access is available here: [Get Seedance 2.5 Early Access](https://evolink.ai/launch/seedance-2-5?utm_source=github&utm_medium=readme&utm_campaign=evolink-agent-skills).

## Install

Install the npm package and copy all skills into an agent project:

```bash
npx evolink-agent-skills -y --path ./my-agent-project --all
```

Install one skill at a time:

```bash
npx skills add Evolink-AI/evolink-agent-skills --skill image-edit -g
npx skills add Evolink-AI/evolink-agent-skills --skill product-image-generation -g
npx skills add Evolink-AI/evolink-agent-skills --skill image-to-video -g
npx skills add Evolink-AI/evolink-agent-skills --skill product-to-ad -g
npx skills add Evolink-AI/evolink-agent-skills --skill ad-video-generation -g
npx skills add Evolink-AI/evolink-agent-skills --skill product-demo-video -g
npx skills add Evolink-AI/evolink-agent-skills --skill ad-creative-images -g
npx skills add Evolink-AI/evolink-agent-skills --skill ugc-video-ads -g
```

Each skill also has its own npm package:

```bash
npx evolink-image-edit -y --path ./my-agent-project
npx evolink-product-image-generation -y --path ./my-agent-project
npx evolink-image-to-video -y --path ./my-agent-project
npx evolink-product-to-ad -y --path ./my-agent-project
npx evolink-ad-video-generation -y --path ./my-agent-project
npx evolink-product-demo-video -y --path ./my-agent-project
npx evolink-ad-creative-images -y --path ./my-agent-project
npx evolink-ugc-video-ads -y --path ./my-agent-project
```

## First Batch

| Skill | Distribution intent | Default model path |
|---|---|---|
| `image-edit` | Edit, retouch, replace background, expand, local changes | GPT Image 2 |
| `product-image-generation` | Product images, ecommerce images, product ad images | GPT Image 2 |
| `image-to-video` | Turn an image into a short video | Seedance 2 |
| `product-to-ad` | Product image or description to ad image and ad video | GPT Image 2 -> Seedance 2 |
| `ad-video-generation` | Ad videos, short-form marketing videos | Seedance 2, optionally GPT Image 2 first frame |
| `product-demo-video` | Ecommerce, SaaS, app, and tool demo videos | GPT Image 2 -> Seedance 2 |
| `ad-creative-images` | Paid social ad images and marketing creatives | GPT Image 2 |
| `ugc-video-ads` | UGC-style video ads, spokesperson hooks, testimonial concepts | Seedance 2 |

## Attribution

All public EvoLink links in this repo use:

```text
utm_source=skillssh&utm_medium=skill&utm_campaign=<skill-name>
```

Keep campaign names identical to skill slugs so analytics can connect installs, first generation, and token consumption.

## Workflow Loop

1. User installs a task or scene skill from skills.sh.
2. Agent uses GPT Image 2 to create or edit source assets when needed.
3. Agent uses Seedance 2 to generate video from the idea, image, or product context.
4. Agent proposes variants, edits, or platform adaptations.
5. EvoLink attributes token consumption to the skill campaign.

## Publishing Order

1. `image-edit`
2. `product-image-generation`
3. `image-to-video`
4. `product-to-ad`
5. `ad-video-generation`
6. `product-demo-video`
7. `ad-creative-images`
8. `ugc-video-ads`

After each publish, install the skill, verify the skills.sh page, validate all links, and run one real EvoLink generation before releasing the next skill.