# pixelbin

Adopt this skill: https://proskills.md/skills/other/anandpareek-hub-pixelbin-claude-skill-skills-pixelbin

Page: https://proskills.md/skills/other/anandpareek-hub-pixelbin-claude-skill-skills-pixelbin
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/pixelbin/SKILL.md
size: 8066
upstream: https://github.com/anandpareek-hub/pixelbin-claude-skill/blob/main/skills/pixelbin/SKILL.md

````text
---
name: pixelbin
description: Use when the user wants to generate AI images or videos, transform/edit existing media, build production media pipelines, get CDN URLs for images/videos, do bulk image processing (background removal, watermark removal, upscaling, resizing), generate SEO content for pages, or build landing pages with AI-generated visuals. Powered by PixelBin's 85+ AI APIs and 60+ URL-based transformations.
---

# PixelBin Claude Skill

Turn Claude into a full media pipeline. Generate, transform, store, and deliver images & videos at scale using PixelBin.

## When to use

- User wants to generate images (nanoBanana, nanoBanana 2, nanoBanana Pro)
- User wants to generate videos (Sora 2, Veo 3, Kling 3, Hailuo, Seedance, LTX-2, Wan)
- User wants to remove backgrounds, watermarks, or upscale images/videos in bulk
- User wants permanent CDN URLs for media
- User wants to build URL-based image transformations (resize, crop, format, quality, etc.)
- User wants to generate SEO content (titles, meta, FAQ schema, briefs)
- User wants to build a landing page with AI-generated images stitched together
- User mentions "PixelBin", "nano banana", "build a media pipeline", "bulk image processing"

## First-run behaviour (IMPORTANT)

Read [`INTRO.md`](INTRO.md) before responding. INTRO.md is the user-facing voice of this skill — match its tone and follow its "How Claude should respond" section.

**If the user has already stated a clear goal** (e.g. "generate 6 hero images for X", "remove backgrounds from these photos", "build a landing page for Y"):
1. Confirm `.env` and `node_modules/` are ready (see Setup check below) — auto-fix silently if you can.
2. **Confirm model + key options in ONE friendly line** (don't make them write JSON — give a default they can accept with "go"):
   - **Image gen:** _"Quick pick: **nano banana 2** (default, balanced) or **nano banana Pro** (premium quality, slower)? Aspect: 1:1 / 16:9 / 9:16 / 4:5 (default 1:1). Resolution: 1K / 2K / 4K (default 2K). Or just say 'defaults' and I'll use nano banana 2 · 1:1 · 2K."_
   - **Video gen:** _"Quick pick: **Veo 3 Fast** (default, balanced cost), **Veo 3** (premium), **Sora 2** (with audio), **Kling 3** (cinematic), or **Hailuo 2.3** (1080p)? Duration: 4 / 6 / 8s (default 6). Aspect: 16:9 / 9:16 / 1:1 (default 16:9)."_
   - **Resize/format:** safe to default silently → `t.resize(...)~t.toFormat(f:webp)~t.compress()`.
   - If the user already specified everything in their prompt, skip the picker and just run.
3. Run the right scripts under the hood and hand back CDN URLs.

**If the user is just exploring** ("hi", "what can you do?", "help"):
1. Greet them and present the **broad buckets** from INTRO.md (image gen, image edit, transformation, AI cleanup, video, bulk, SEO, landing pages).
2. Show **one concrete example prompt + a sample CDN URL** from INTRO.md so it feels real and easy.
3. Invite them to just say what they want in plain English. No CLI talk.

**Default to chat-first.** Don't expose CLI flags, JOBS arrays, model names, or transform syntax unless the user asks "how does this work?". Run scripts silently; report results visually.

## Handling images the user provides (CRITICAL)

When the user references an image, **you must obtain it yourself** — never ask them to "give me a file path" or "save it to Downloads". The image is already accessible to you in one of these forms:

| What the user did | What you do |
| --- | --- |
| **Pasted an image inline in the chat** | The image is in your conversation context. Use the `Write` tool to save the bytes to `./scripts/_inputs/<slug>.<ext>`, then upload it via `pixelbin.assets.fileUpload({ file: fs.createReadStream(...) })` to get a permanent CDN URL. Pass that URL into `images: [...]` for the prediction. |
| **Gave you a public URL** (e.g. `https://example.com/photo.jpg`, a CDN URL, a Slack/Drive public link) | Two options:<br>• **Quick path** — pass the URL straight into `images: [url]` of `pixelbin.predictions.createAndWait` (most models accept a URL). No upload needed.<br>• **Permanent path** — call `pixelbin.assets.urlUpload({ url, path: '<folder>', name: '<slug>', access: 'public-read' })` to store it in PixelBin DAM, then use the resulting CDN URL. |
| **Gave a local path** (`~/Downloads/photo.jpg`, `./photo.jpg`) | Use `pixelbin.assets.fileUpload({ file: fs.createReadStream(absPath), ... })`. |
| **Mentioned an image but didn't attach or link it** | _Now_ ask — but politely: _"Drop the image into the chat or paste a URL — I'll handle the rest."_ |

**Never** say "the inline image isn't saved on disk, please paste the path" — that's a user-experience failure. Saving inline image bytes to disk is your job, not theirs.

## Cost-aware path selection (CRITICAL)

**Before reaching for a generation model, decide whether the task needs generation at all.** Generation models are the most expensive op in the stack. For most product / e-commerce / variant tasks, you can do the same job with a cheap prediction + free URL transforms.

### Decision tree

| User intent | Cheap path (use this) | Expensive path (avoid unless asked) |
| --- | --- | --- |
| **"Same product, white bg, marketplace-ready"** (Amazon, Shopify, Flipkart, etc.) | 1. `erase_bg` prediction → transparent PNG<br>2. Upload to DAM<br>3. URL transform: `t.extend(...,bc:ffffff)~t.resize(h:H,w:W)~t.toFormat(f:webp)~t.compress()` | nanoBanana regenerate (loses product fidelity, ~10× cost) |
| **"Resize / reformat / compress / different aspect ratio"** for an existing image | URL transforms only — `t.resize`, `t.toFormat`, `t.compress`, `t.extend` (free, just CDN params) | Regeneration |
| **"Upscale to 4K"** | `vsr_upscale` prediction (or `t.resize` if source is large enough) | Regeneration at higher res |
| **"Remove watermark"** | `wm_remove` / `wmrPro_remove` / `wmrMax_remove` prediction | Regeneration |
| **"Remove background and place on new scene"** | `erase_bg` + composite via `t.merge` / generation only for the new background | Full regeneration of the whole image |
| **"Generate a NEW scene / NEW product shot / hero image from scratch"** | Generation model (nanoBanana 2 / Pro) — this is the right tool | — |
| **"Variants of the same hero (color, angle, style change)"** | Image-to-image with `nanoBanana2_generate` + `images:[ref]` (preserves identity) | Text-only regeneration (loses identity) |

### Cost ranking (rough, lower → cheaper)
1. **URL transforms** — free, no API call
2. **Plugin transforms** in URL (when activated) — free per request, included in plan
3. **Predictions: `erase_bg`, `wm_remove`, `vsr_upscale`** — small per-call credit cost
4. **Image generation** — `nanoBanana_generate` < `nanoBanana2_generate` < `nanoBananaPro_generate`
5. **Video generation** — most expensive op; always confirm before spending

### Worked example — "Amazon + Shopify + Instagram-ready, white bg, 4K, 1:1 + 9:16"

**Wrong** (what NOT to do): regenerate each variant with nanoBanana — 12 outputs × generation cost, plus product hallucination risk.

**Right** (default behavior):
```
For each source image:
  1. urlUpload(source)                                        → CDN URL
  2. predictions.createAndWait({ name: 'erase_bg', input: { image: cdnUrl } })  → transparent PNG
  3. urlUpload(eraseBgOutput)                                 → CDN URL of transparent product
  4. Build transform URLs (no API call):
     • Amazon 1:1   t.extend(t:200,r:200,b:200,l:200,bc:ffffff)~t.resize(h:2048,w:2048)~t.toFormat(f:jpeg)~t.compress()
     • Shopify 1:1  t.extend(t:150,r:150,b:150,l:150,bc:ffffff)~t.resize(h:2048,w:2048)~t.toFormat(f:webp)~t.compress()
     • Instagram 9:16  t.extend(t:600,r:200,b:600,l:200,bc:ffffff)~t.resize(h:1920,w:1080)~t.toFormat(f:webp)~t.compress()
```

This costs **~1 prediction per source image**, vs **3 generations per source**. Same visual result, fraction of the credits, zero product drift.

### When in doubt — ask the user
If a task is borderline (e.g. "make 
````

## File: README.md
upstream: https://github.com/anandpareek-hub/pixelbin-claude-skill/blob/main/README.md

````text
<div align="center">

<a href="https://www.pixelbin.io/?utm_source=github&utm_medium=claude-skill&utm_campaign=logo">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://cdn.pixelbin.io/v2/round-dust-e06b92/t.resize(h:80)/pixelbin-claude-skill-samples/pixelbin-logo-white.png" />
    <img src="https://cdn.pixelbin.io/v2/round-dust-e06b92/t.resize(h:80)/pixelbin-claude-skill-samples/pixelbin-logo-black.png" alt="Fynd Pixelbin" height="64" />
  </picture>
</a>

# PixelBin Claude Skill

**Turn Claude into a full media pipeline for AI image generation, AI video generation, image transformation, background removal, watermark removal, image upscaling, and bulk image processing — backed by a global image CDN and DAM.**

> Claude skill for AI image generation (nanoBanana / nanoBanana 2 / nanoBanana Pro), AI video generation (Sora 2, Veo 3, Kling 3, Hailuo, Seedance, LTX-2, Wan 2.5), 60+ chainable image transformation operations (resize, crop, WebP/AVIF format conversion, watermark, compress, sharpen, smart-crop), background remover, watermark remover, AI image upscaler, photo restoration, colorization, OCR, image editing, and image-to-video — delivered over a built-in CDN with DAM.

[![Get API Key](https://img.shields.io/badge/Get_API_Key-Free_Tier-2563eb?style=for-the-badge)](https://www.pixelbin.io/?utm_source=github&utm_medium=claude-skill&utm_campaign=signup)
[![Pricing](https://img.shields.io/badge/Pricing-View_Plans-10b981?style=for-the-badge)](https://www.pixelbin.io/pricing?utm_source=github&utm_medium=claude-skill&utm_campaign=pricing)
[![Docs](https://img.shields.io/badge/Docs-PixelBin-6366f1?style=for-the-badge)](https://www.pixelbin.io/docs?utm_source=github&utm_medium=claude-skill&utm_campaign=docs)
[![License](https://img.shields.io/badge/License-MIT-374151?style=for-the-badge)](LICENSE)

</div>

---

## 🚀 The Wow

> **"Drop 50 product photos in a Claude conversation. Get back e-commerce-ready images — backgrounds removed, upscaled to 4K, watermarked, resized for Amazon, Shopify, and Instagram — in one prompt."**

That's not a roadmap. That's what this skill does, today.

---

## ✨ Created with just one prompt

<table>
  <tr>
    <td align="center" width="20%">
      <img src="https://cdn.pixelbin.io/v2/dummy-cloudname/original/__pixelbin_console_assets/__ai_image_generator/templates/create-a-hero-shot/preview.jpg" width="200" /><br />
      <sub><b>Hero shot</b></sub>
    </td>
    <td align="center" width="20%">
      <img src="https://cdn.pixelbin.io/v2/dummy-cloudname/original/__pixelbin_console_assets/__ai_image_generator/templates/floating-product-photo/preview.jpg" width="200" /><br />
      <sub><b>Floating product</b></sub>
    </td>
    <td align="center" width="20%">
      <img src="https://cdn.pixelbin.io/v2/dummy-cloudname/original/__pixelbin_console_assets/__ai_image_generator/templates/editorial-fashion-photo/preview.jpg" width="200" /><br />
      <sub><b>Editorial fashion</b></sub>
    </td>
    <td align="center" width="20%">
      <img src="https://cdn.pixelbin.io/v2/dummy-cloudname/original/__pixelbin_console_assets/__ai_image_generator/templates/product-in-lifestyle-scene/preview.jpg" width="200" /><br />
      <sub><b>Lifestyle scene</b></sub>
    </td>
    <td align="center" width="20%">
      <img src="https://cdn.pixelbin.io/v2/dummy-cloudname/original/__pixelbin_console_assets/__ai_image_generator/templates/cinematic-frame/preview.jpg" width="200" /><br />
      <sub><b>Cinematic frame</b></sub>
    </td>
  </tr>
</table>

📸 **See more →** [`SHOWCASE.md`](SHOWCASE.md)

---

## 🆚 How this is different

Most AI-media skills give Claude a single API call. PixelBin gives Claude a **production media stack**.

| Generic AI media skills | **PixelBin Claude Skill** |
| --- | --- |
| One-off API calls | **Full media pipeline** — generate → store → transform → deliver |
| Image gen, OCR, bg-remove… | **85+ AI APIs**: image gen, video gen, OCR, upscale, bg-remove, watermark remove, restore, colorize, expand, relight, frame-interp, video upscale, video watermark remove, +many more |
| Stateless, no CDN | **Built-in global CDN** — edge cache, HTTP/3, signed URLs, custom domains |
| Per-call billing | **URL-param transformations** — chain `t.resize()~t.toFormat(f:webp)~t.compress()` infinitely, free |
| No bulk pipelines | **Built for batch** — process hundreds in one job, resumable |
| Just an API | **Includes DAM** — folders, tags, search, access controls, bulk ops |

> 📌 **Powered by the same media infrastructure trusted by enterprise retail brands in production.**

---

## 🧰 What's inside

### 1. **85+ AI APIs for image generation, video generation & editing**
   AI image generation (nanoBanana, nanoBanana 2, nanoBanana Pro), AI video generation (Sora 2, Veo 3, Kling 3, Hailuo, Seedance, LTX-2, Wan 2.5), background removal, watermark removal, AI image upscaling, video upscaling, OCR, photo restoration, colorization, image expansion (outpainting), AI relighting, object removal, frame interpolation, image captioning, sketch-to-image, image-to-video, AI photo editor, and more. → [`references/apis.md`](references/apis.md)

### 2. **60+ image transformation operations** — chainable in one URL
   Image resize, crop, format conversion (WebP / AVIF / JPEG / PNG), quality / compression, watermark, blur, sharpen, brightness, saturation, rotation, padding, tinting, smart-crop, focal-point cropping, art-style presets, and more — all chainable in a single CDN URL with no extra API call. → [`references/transformations.md`](references/transformations.md)

### 3. **Built-in image & video CDN** — global edge delivery
   Every uploaded asset gets a `cdn.pixelbin.io/v2/...` URL with HTTP/3, edge caching, signed URLs, and custom domains — production-grade image CDN and video CDN out of the box. → [`references/cdn.md`](references/cdn.md)

### 4. **DAM (Digital Asset Management)** for images & videos
   Folders, tags, full-text search, access controls (`public-read` / `private`), bulk ops, metadata. Manage thousands of images and videos without spinning up your own storage layer.

### 5. **Bulk image processing & batch pipelines**
   Concurrency-safe batch runners, resumable jobs, progress checkpointing. Bulk image generation (500+ images while you sleep), bulk image transformation (10,000+ product shots in a script), bulk background removal, bulk watermark removal, bulk image upscaling.

---

## 📦 What you can build

| Use case | Tools used | Live page |
| --- | --- | --- |
| 🛍️ E-commerce hero shots at scale | image-gen + bg-remove + upscale + resize | [AI Image Generator](https://www.pixelbin.io/ai-tools/ai-image-generator?utm_source=github&utm_medium=claude-skill) |
| 🧹 Bulk watermark cleanup | watermark-remover | [Watermark Remover](https://www.pixelbin.io/ai-tools/remove-watermark?utm_source=github&utm_medium=claude-skill) |
| 🔍 4K upscaling for print/marketing | image-upscale | [AI Image Upscaler](https://www.pixelbin.io/ai-tools/ai-image-upscaler?utm_source=github&utm_medium=claude-skill) |
| ✂️ One-click background removal | bg-remove | [Remove Background](https://www.pixelbin.io/ai-tools/remove-background-from-image?utm_source=github&utm_medium=claude-skill) |
| 🎬 AI video generation (text/image → video) | video-gen (Veo 3 / Sora 2 / Kling 3) | [AI Video Generator](https://www.pixelbin.io/ai-tools/ai-video-generator?utm_source=github&utm_medium=claude-skill) |
| 🎨 AI image editing (inpaint, expand, relight) | nanoBanana 2 / Pro | [AI Photo Editor](https://www.pixelbin.io/ai-tools/ai-photo-editor?utm_source=github&utm_medium=claude-skill) |
| 🌈 Old photo restoration & colorization | restore + colorize | [Photo Restoration](https://www.pixelbin.io/ai-tools/photo-restoration?utm_source=github&utm_medium=claude-skill) |
| 📄 Landing-page generation (SEO + images) | seo-content + image-gen + build-page | — |

---

## ⚡ Quickstart (3 steps, ~2 minutes)

### 1. Install

```bash
git clone https://github.com/anandpareek-hub/
````
