NewUGC ads, product motion and client finder skills

imageat skills
for your AI agent

Five SKILL.md files for Claude Code, claude.ai, Codex, Cursor and any agent that reads them. Install once, and your agent can generate images and videos, make UGC and product ads, produce explainers and find clients for your work.

Pick a skill

Core

imageat API

imageat

Generate and edit images, create videos, poll jobs and check your balance through the imageat API.

“Generate a product photo of a ceramic mug on sculpted stone with imageat”

Video ads

UGC ads

imageat-ugc-ads

Researches what converts in your niche, writes hook-first scripts, builds the actor and location as images, then animates them with Seedance 2.5.

“Make 3 UGC ads for my insulated water bottle, 9:16”

Motion ads

Product motion

imageat-product-motion

Turns a product photo or logo into a hyper-motion, motion-graphics or cinematic ad: product read, lighting stills, approved storyboard, render.

“Turn this sneaker photo into a 15-second hyper motion ad”

Faceless video

Explainer video

imageat-explainer-video

Researches a topic, writes a fact-checked script and delivers one narrated, subtitled mp4 in a collage or paper-diorama style.

“Make a one-minute explainer about why shipping costs spiked”

Sell your work

Client finder

imageat-client-finder

Finds businesses with a visible content problem, makes each a free imageat sample and drafts personal pitch emails you approve before Gmail sends them.

“Find 10 kitchenware shops in Texas that need better product photos”

Motion Pack · motion graphics from one promptPaid skill pack: script, voiceover, word captions and animated 1080×1920 video, rendered on your computer. One-time payment.See examples

Install in your agent

  1. 1

    Add the imageat marketplace

    Run this inside Claude Code.

    Claude Code
    /plugin marketplace add incendies/imageat-skills
  2. 2

    Install the plugin

    This adds all five skills. Update later with /plugin marketplace update imageat.

    Claude Code
    /plugin install imageat@imageat
  3. 3

    Set your API key

    Create a key on your Projects page and export it in your shell profile (for example ~/.zshrc).

    Shell
    export IMAGEAT_API_KEY="iat_live_xxxxxxxxxxxx"
  4. 4

    Ask your agent

    Try “Make 3 UGC ads for my insulated water bottle”. The agent loads the matching skill, calls imageat and returns the finished URLs.

What every skill
can call on imageat

Generate images

Text-to-image and reference-guided edits with up to 4K output and CDN-hosted URLs.

Edit photos

Background removal and replacement, object eraser, inpainting, relight, virtual try-on and more.

Create videos

Text, image and reference-to-video jobs that the agent polls until the finished URL is ready.

Spend carefully

Credit estimates up front, balance checks, idempotent retries and a confirm before large batches.

Image models

Nano Banana ProNano Banana 2.1Krea 3Nano Banana 2GPT Image 2.5Midjourney V8GPT Image 2Kling Image 4.0Seedream 5.5Seedream 5 ProNano Banana 2 LiteNano BananaKrea 2 LargeKrea 2 Medium

Video models

Gemini Omni Flash 1.2Kling 4.0FLUX 3 MaxWan 3.0MiniMax H3 MaxSeedance 2.5Seedance 2.5 FlashMidjourney V8Pixverse V6Veo 3.1 FastVeo 3.1 LiteSoraKling 2.6Kling 3.0Kling 3.0 OmniGrok VideoGrok Video 1.5Seedance 2.0Seedance 2.0 MiniGemini Omni FlashHappy Horse 1.0Happy Horse 1.0 ReferenceFLUX 3 Video

Model lists come from the live API catalog. Prices: API pricing.

Read the source

imageat/SKILL.md
---
name: imageat
description: Generate AI images and videos with the imageat API. Use when the user asks to create, edit or animate images, remove a background, generate a video from text or a photo, or check their imageat balance.
---

# imageat

imageat generates images and videos from prompts and reference images. Every call is
billed to the user's imageat account, so confirm before generating many outputs or
long videos.

## Setup

- The user creates an API key at https://imageat.com/projects/keys (keys start with
  `iat_live_`). Read it from the `IMAGEAT_API_KEY` environment variable; never print it.
  If it is not set, ask the user to set it (or paste a key) before calling the API.
- Base URL: `https://imageat.com/api/v1`
- Send `Authorization: Bearer $IMAGEAT_API_KEY` and `Content-Type: application/json`.
- Send an `Idempotency-Key` header (any unique string) on POSTs you might retry.
- MCP clients can connect to https://mcp.imageat.com/mcp instead (OAuth or the same key).

## Generate an image (synchronous)

```bash
curl -X POST "https://imageat.com/api/v1/images" \
  -H "Authorization: Bearer $IMAGEAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nano-banana-2","prompt":"A cinematic product photo on sculpted stone","aspectRatio":"1:1","resolution":"1K","numImages":1}'
```

The response contains `url` (one image) or `urls` (several), hosted on cdn.imageat.com.

Models (live list: `GET https://imageat.com/api/v1/models/images`):

- `nano-banana-pro` (Nano Banana Pro): High-fidelity generation and editing with up to 4K output. From $0.40 / image.
- `nano-banana-2.1` (Nano Banana 2.1): Google's newest Nano Banana: up to 4K, extreme 8:1 to 1:8 ratios, up to 14 references, and optional web search grounding. From $0.16 / image.
- `krea-3` (Krea 3): Krea's newest model: aesthetic generation with prompt expansion, faithful instruction edits, up to 4 references, 1K or 2K. From $0.06 / image.
- `nano-banana-2` (Nano Banana 2): Fast, cost-efficient generation for iterative creative work. From $0.16 / image.
- `gpt-image-2.5` (GPT Image 2.5): OpenAI's newest image model: five quality tiers, scoped edits, and transparent cut-outs. Add gpt-image-2.5-sunburst for the slower, finer-detail variant. From $0.02 / image.
- `midjourney-v8` (Midjourney V8): Midjourney V8.2 with stylize, chaos, weird, and style references. Every run returns 4 images; native 2K HD optional. From $0.18 / 4 images.
- `gpt-image-2` (GPT Image 2): Precise instruction following with selectable quality tiers. From $0.02 / image.
- `kling-image-4` (Kling Image 4.0): Kling's newest image model: 2K or 4K stills and edits with up to 10 reference images for identity and style. From $0.13 / image.
- `seedream-5.5` (Seedream 5.5): ByteDance's newest Seedream: 1K or 2K generation and edits with up to 10 reference images. From $0.06 / image.
- `seedream-5.0-pro` (Seedream 5 Pro): High-fidelity ByteDance generation and reference-guided editing. From $0.14 / image.
- `nano-banana-2-lite` (Nano Banana 2 Lite): The cheapest Nano Banana, for drafts, thumbnails and bulk runs. From $0.08 / image.
- `nano-banana` (Nano Banana): The original Nano Banana (Gemini 2.5 Flash Image) for quick generation and edits. From $0.16 / image.
- `krea-2-large` (Krea 2 Large): Krea 2 text-to-image with up to 10 style references. One image per request. $0.13 / image.
- `krea-2-medium` (Krea 2 Medium): Lighter Krea 2 with the same style references. One image per request. $0.07 / image.

- GPT Image models accept `quality`; GPT Image 2.5 also takes `xhigh`/`max` and
  `transparentBackground` (needs png or webp output).
- Nano Banana 2.1 takes up to 14 `images`, extreme ratios (`8:1` to `1:8`, plus `auto`)
  and `enableWebSearch` for grounding in live web results.
- Krea 3 (`krea-3`) renders 1K or 2K (4K requests render at 2K) and takes up to 4 `images`;
  each reference is billed like extra output pixels, so send only the ones the edit needs.
- Midjourney V8 (`midjourney-v8`) always returns 4 images per run (read `urls`; `numImages`
  is ignored) and takes ~2 minutes. `resolution` is 1K or 2K (native HD); optional `stylize`
  (0-1000), `chaos` (0-100), `weird` (0-3000), `seed` and `styleReferenceUrl`.
- Editing / reference-guided generation: pass public URLs or base64 data URLs in `images`.
- Other fields: `aspectRatio`, `resolution` (1K, 2K, 4K), `outputFormat` (png, jpeg, webp), `numImages`.

## Edit an image

`GET https://imageat.com/api/v1/edit/features` lists the edit features (id, name, credit cost): background
removal and replacement, object eraser, inpainting, relight, virtual try-on and more.

```bash
curl -X POST "https://imageat.com/api/v1/edit" \
  -H "Authorization: Bearer $IMAGEAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"feature":"ideogram-remove-background","imageUrl":"https://example.com/photo.jpg"}'
```

Body: `feature`, `imageUrl` (public URL or base64 data URL), plus `prompt`, `maskUrl`,
`backgroundPrompt` or `backgroundImageUrl` when the feature needs them.

## Generate a video (asynchronous)

```bash
curl -X POST "https://imageat.com/api/v1/videos" \
  -H "Authorization: Bearer $IMAGEAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedance25","providerVariant":"more","prompt":"A paper airplane glides through a softly lit studio","duration":"5s","resolution":"720p","aspectRatio":"adaptive"}'
```

The response has `status: pending`, `taskId` and `generationId`. Poll every 5-10 seconds:

```bash
curl "https://imageat.com/api/v1/videos/status?taskId=TASK_ID&generationId=GENERATION_ID" \
  -H "Authorization: Bearer $IMAGEAT_API_KEY"
```

Stop when `status` is `completed` (read `url`) or `failed`. Cancel with `POST https://imageat.com/api/v1/videos/cancel` and body
`{"taskId":"TASK_ID","generationId":"GENERATION_ID"}`.

Models (live list: `GET https://imageat.com/api/v1/models/videos`):

- `gemini-omni-12` (Gemini Omni Flash 1.2): Text, image, first/last-frame (≤10s) or reference-image (up to 10) video, 16:9 or 9:16; 3–15s · 360p/720p/1080p/4K · audio; From $0.055/sec.
- `kling4` (Kling 4.0): Text, image, first/last-frame, reference-image (up to 10) or video edit (mode edit-video, billed per source second); 3–30s · 720p/1080p; From $0.32/sec.
- `flux3-max` (FLUX 3 Max): Text, image, or first/last-frame video (firstFrameUrl + lastFrameUrl); 5–20s · 720p/1080p · audio; From $1.71.
- `wan3` (Wan 3.0): Text, image, first/last-frame or reference-image video; 2–30s · 480p/720p/1080p · audio; From $0.20.
- `minimax-h3-max` (MiniMax H3 Max): Text, image, or first/last-frame video; 5–15s · 480p/768p; From $0.50.
- `seedance25` (Seedance 2.5): Text, image, reference, or frame-controlled video; 4–30s · 480p/720p; From $0.83.
- `seedance25-flash` (Seedance 2.5 Flash): Faster, cheaper Seedance 2.5: text, image, reference, or first/last-frame video; 4–30s · 480p/720p; From $0.57.
- `midjourney-v8` (Midjourney V8): Image-to-video, 4 clips per run; 4 × 5s · 480p/720p; From $0.18.
- `pixverse` (Pixverse V6): Text/image video with optional audio; 1–15s · up to 1080p; From $0.09/sec.
- `veo` (Veo 3.1 Fast): Default model. Text or image video; 4/6/8s · 720p/1080p/4K · audio; From $1.20.
- `veo-lite` (Veo 3.1 Lite): Text, image, or first/last-frame video; 4/6/8s · 720p/1080p · audio; From $0.40.
- `sora` (Sora): Text or image video; 4/8/12s · 720p/1080p; From $0.80.
- `kling` (Kling 2.6): Text or image video; 5/10s · 720p/1080p · optional audio; From $0.70.
- `kling3` (Kling 3.0): Text or image video; 3–15s · 720p/1080p/4K · optional audio; From $0.34/sec.
- `kling3-omni` (Kling 3.0 Omni): Text or image video; 3–15s · 720p/1080p/4K · optional audio; From $0.42/sec.
- `grok` (Grok Video): Text or image video; 1–15s · 480p/720p; From $0.10/sec.
- `grok-1-5` (Grok Video 1.5): Image-to-video; 1–15s · 480p/720p; From $0.17/sec.
- `seedance2` (Seedance 2.0): Text, image, or reference-image video; 4–15s · 480p/720p/1080p; From $1.08.
- `seedance2-mini` (Seedance 2.0 Mini): Text, image, or reference-image video; 5/10/15s · 480p/720p; From $0.36.
- `gemini-omni` (Gemini Omni Flash): Text or image video; 5/10s · 720p; From $2.12.
- `happyhorse` (Happy Horse 1.0): Text or image video; 5/10/15s · 720p/1080p; From $1.40.
- `happyhorse-ref` (Happy Horse 1.0 Reference): Reference-image video (referenceImageUrls); 5/10/15s · 720p/1080p; From $1.40.
- `flux3` (FLUX 3 Video): Text or image video; 5–20s · 720p/1080p; From $1.70.

- Image-to-video: pass `imageUrl` (first frame), or `firstFrameUrl` + `lastFrameUrl`.
- `midjourney-v8` is image-to-video only: `imageUrl` is required, `resolution` is 480p or 720p,
  `motion` is low or high. Each run returns 4 five-second clips in `urls`.

## Post to social accounts (Social Hub)

The user connects Instagram, Facebook Pages, LinkedIn, X and others at
https://imageat.com/social-hub. Posting spends no credits but needs an imageat plan.

1. `GET https://imageat.com/api/v1/social/accounts` lists connected accounts with `can_publish` and a `reason` when false.
2. `POST https://imageat.com/api/v1/social/posts` with `account_ids`, `caption` (optional per-account `captions`),
   media as `generation_id` or `media_url` (JPEG/PNG/WebP or MP4), and `mode`:
   `draft` (default), `schedule` (+ `scheduled_at`, ISO 8601, `timezone`) or `publish`.
3. `GET https://imageat.com/api/v1/social/posts/{id}` shows each destination's status and `published_url`.
   Videos may stay `publishing` for a minute while the platform processes them.
4. `DELETE https://imageat.com/api/v1/social/posts/{id}` cancels a draft or scheduled post.
5. `GET https://imageat.com/api/v1/social/autopilots` and `POST https://imageat.com/api/v1/social/autopilots/{id}/queue` with
   `items: [{ caption, generation_id | media_url }]` fill the user's weekly posting slots.

Publishing is public: show the user the caption, media and accounts and get their OK before
`publish` or `schedule`. A `402` with `code: "plan_required"` means the plan does not cover
posting (or that account); send the user to https://imageat.com/pricing.

## Check balance

`GET https://imageat.com/api/v1/credits` returns the account's API balance in USD (and spendable web
credits, which are spent first).

## Errors

- `401`: missing or invalid key. Ask the user for a valid key.
- `402`: not enough balance (`balance` and `required` in the body). Send the user to
  https://imageat.com/api-pricing; do not retry.
- `429`: rate limited. Wait for `Retry-After` seconds, then retry.
- `500`: retry once with the same `Idempotency-Key`.

## Reference

- Full API docs (markdown): https://imageat.com/docs/api/md
- OpenAPI: https://imageat.com/openapi.yaml
- Pricing: https://imageat.com/api-pricing

Skill or MCP server?

Agent skills

Teach the agent a workflow and how to call imageat. Best for Claude Code, Codex and other agents that can run commands.

MCP server

Adds ready-made imageat tools and signs in with your account. Best for claude.ai, ChatGPT and Cursor. Works alongside the skills.

Set up MCP

Questions, answered

SKILL.md files that teach AI agents how to work with imageat. The core skill covers the API: images, edits, videos and your balance. The others are full workflows: UGC ads, product motion ads, explainer videos and finding clients for your content. Agents load a skill only when your request matches it.

Give your agent a studio

One install, five skills, billed to the same imageat account.