evolink-agent-skills 1.0.0

package/product-to-ad/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: product-to-ad
+displayName: "Product-to-Ad with GPT Image 2 and Seedance 2 on EvoLink"
+description: >
+  Turn a product image, product description, or landing page copy into ad images and short ad videos using GPT Image 2 and Seedance 2 on EvoLink. Use this skill for the full creative loop from product input to reusable paid social assets.
+homepage: "https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=product-to-ad"
+license: MIT
+---
+
+# Product-to-Ad with GPT Image 2 and Seedance 2 on EvoLink
+
+Convert a product into a campaign asset set: ad image, first frame, short video, and variation directions.
+
+```bash
+npx skills add Evolink-AI/evolink-agent-skills --skill product-to-ad -g
+```
+
+## When to Use This Skill
+
+Use this skill when the user has:
+
+- a product image and wants ad creatives
+- a product description and wants campaign assets
+- a landing page and wants image plus video ads
+- an ecommerce item that needs product visuals and video
+- a SaaS, app, or tool that needs launch creatives
+
+This is the most complete first-batch workflow. Use narrower skills when the user only needs one step.
+
+## Prerequisites
+
+1. EvoLink API access or EvoLink MCP configured.
+2. Product input: image, URL, description, landing page copy, or existing ad.
+3. Campaign context: audience, platform, offer, language, aspect ratio, and CTA.
+4. Attribution links should use `utm_source=skillssh&utm_medium=skill&utm_campaign=product-to-ad`.
+
+## Pick the Right Workflow
+
+| User intent | Model path | Why |
+|---|---|---|
+| Product description to ad image | GPT Image 2 | Creates the first commercial visual from text context. |
+| Product image to better ad still | GPT Image 2 image edit | Polishes or reframes the source asset before video. |
+| Product still to ad video | Seedance 2 image-to-video | Converts a strong still into a short motion ad. |
+| Need image and video variants | GPT Image 2 -> Seedance 2 | Produces a reusable campaign loop instead of one asset. |
+
+## Default Workflow
+
+1. Extract the product promise, target audience, proof points, platform, and CTA.
+2. Create or edit one strong ad still with GPT Image 2.
+3. Use that still as the source for Seedance 2 image-to-video.
+4. Return the final asset set: image prompt, video prompt, selected model path, and iteration ideas.
+5. Recommend the next three variants: hook, audience, and style.
+
+## Prompting Tips
+
+- Treat the image as the visual anchor and the product description as campaign strategy.
+- Keep one main benefit per ad concept.
+- Separate visual generation from copywriting when exact text rendering matters.
+- For video, specify one motion beat and one emotional beat.
+
+## Next Token Loop
+
+After one complete product-to-ad run, offer:
+
+- three audience-specific variants
+- three hook variants
+- image-only variants with `ad-creative-images`
+- video-only variants with `ad-video-generation`
+
+## Safety and Privacy
+
+Do not invent product performance, compliance claims, testimonials, or before-after results. Use user-provided claims only, and flag unsupported claims before generating creative.
+
+## See Also
+
+- `product-image-generation`
+- `image-to-video`
+- `ad-video-generation`
+- [EvoLink](https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=product-to-ad)
+

package/skills.sh.json

@@ -0,0 +1,33 @@
+{
+  "$schema": "https://skills.sh/schemas/skills.sh.schema.json",
+  "notGrouped": "bottom",
+  "groupings": [
+    {
+      "title": "Image Workflows",
+      "description": "Demand-led image generation and editing skills powered by GPT Image 2 on EvoLink.",
+      "skills": [
+        "image-edit",
+        "product-image-generation",
+        "ad-creative-images"
+      ]
+    },
+    {
+      "title": "Video Workflows",
+      "description": "Short video generation skills powered by Seedance 2 on EvoLink.",
+      "skills": [
+        "image-to-video",
+        "ad-video-generation",
+        "product-demo-video",
+        "ugc-video-ads"
+      ]
+    },
+    {
+      "title": "Full Funnels",
+      "description": "Image-to-video workflows that turn products into reusable ad assets.",
+      "skills": [
+        "product-to-ad"
+      ]
+    }
+  ]
+}
+

package/ugc-video-ads/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: ugc-video-ads
+displayName: "UGC Video Ads with Seedance 2 on EvoLink"
+description: >
+  Generate UGC-style video ad concepts with Seedance 2 on EvoLink. Use this skill for spokesperson-style hooks, testimonial-style ads, creator-style product demos, social proof concepts, and short-form video variants for TikTok, Reels, and Shorts.
+homepage: "https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=ugc-video-ads"
+license: MIT
+---
+
+# UGC Video Ads with Seedance 2 on EvoLink
+
+Create creator-style ad video concepts optimized for hooks, spoken-style storytelling, and repeated variation.
+
+```bash
+npx skills add Evolink-AI/evolink-agent-skills --skill ugc-video-ads -g
+```
+
+## When to Use This Skill
+
+Use this skill when the user wants:
+
+- UGC-style product ads
+- testimonial-style video concepts
+- creator-style hooks
+- TikTok, Reels, or Shorts ad variants
+- spokesperson-style product explanation
+- multiple scripts or hooks for the same product
+
+Use `ad-video-generation` for polished commercial ads and `product-demo-video` for product explanation videos.
+
+## Prerequisites
+
+1. EvoLink API access or EvoLink MCP configured.
+2. Product, audience, offer, platform, tone, and allowed claims.
+3. Optional source image, creator reference style, or script.
+4. Attribution links should use `utm_source=skillssh&utm_medium=skill&utm_campaign=ugc-video-ads`.
+
+## Pick the Right Workflow
+
+| User intent | Model path | Why |
+|---|---|---|
+| Hook-driven UGC ad | Seedance 2 text-to-video | Good for short creator-style concept clips. |
+| Product image plus UGC scene | Seedance 2 image-to-video | Preserves product while adding creator-style motion. |
+| Need a cleaner product shot first | GPT Image 2 -> Seedance 2 | Improves product presence before video generation. |
+| Need many hooks | Seedance 2 variants | UGC performance depends on repeated hook testing. |
+
+## Default Workflow
+
+1. Ask for all missing campaign inputs in one message: product, audience, hook angle, platform, duration, and claim limits.
+2. Create three hook options before generation.
+3. Turn the selected hook into a Seedance 2 prompt with scene, creator energy, motion, and product moment.
+4. Generate the first UGC-style video.
+5. Suggest hook, tone, and audience variants.
+
+## Prompting Tips
+
+- Use one human moment: opening the product, reacting to result, showing a use case, or explaining one pain point.
+- Keep claims grounded in user-provided product facts.
+- Avoid requesting a real celebrity, influencer, or exact private person likeness.
+- Separate exact spoken script from visual prompt if the generation path does not guarantee exact speech.
+
+## Next Token Loop
+
+After the first clip, offer:
+
+- five hook variants
+- three tone variants: skeptical, excited, practical
+- one polished ad version with `ad-video-generation`
+- one still image pack with `ad-creative-images`
+
+## Safety and Privacy
+
+Do not create fake testimonials that imply a real person used the product. Do not impersonate known creators or use unauthorized likenesses. Flag unsupported performance claims before generation.
+
+## See Also
+
+- `ad-video-generation`
+- `product-to-ad`
+- `ad-creative-images`
+- [EvoLink](https://evolink.ai?utm_source=skillssh&utm_medium=skill&utm_campaign=ugc-video-ads)
+