$npx -y skills add MagicCube/agentara --skill ecom-shotGenerate Nano Banana Pro (Gemini 3 Pro Image) prompts for e-commerce product photography. Given a user-uploaded product photo, this skill identifies the main subject, asks the user to choose a scene type, then outputs a professional, ready-to-paste English prompt optimized for Na
| 1 | # Ecom Shot 📸 |
| 2 | |
| 3 | Generate studio-quality Nano Banana Pro prompts that turn casual product snapshots into professional e-commerce imagery. |
| 4 | |
| 5 | ## How It Works |
| 6 | |
| 7 | This skill acts as a **Creative Director**: it analyzes the uploaded product image, identifies the subject, and crafts a detailed photography-grade prompt that Nano Banana Pro can execute with a reference image. The output is a ready-to-paste English text prompt — the user takes it to Gemini App, Google AI Studio, or any Nano Banana Pro endpoint. |
| 8 | |
| 9 | ## Workflow |
| 10 | |
| 11 | ### Step 1: Validate Input |
| 12 | |
| 13 | 1. Confirm the user has uploaded at least one image. If not, ask them to upload the product photo they want to transform. |
| 14 | 2. Carefully examine the uploaded image(s). Pay attention to: |
| 15 | - What is the **main product/subject**? (e.g., a mechanical watch, a ceramic mug, a pair of sneakers) |
| 16 | - What is the product's **material, color, texture, key visual features**? |
| 17 | - What is the **current context**? (e.g., on a messy desk, held in hand, in packaging) |
| 18 | - Are there any **brand markings, logos, or distinctive design details** worth preserving? |
| 19 | |
| 20 | ### Step 2: Confirm Subject & Gather Preferences |
| 21 | |
| 22 | Use `ask_user_input_v0` to collect the user's preferences in one go: |
| 23 | |
| 24 | **Question 1 — Subject Confirmation** (single_select): |
| 25 | Present what you identified as the main subject and ask the user to confirm or correct. |
| 26 | - Options: your identified subject description, or "其他(我来描述)" |
| 27 | |
| 28 | **Question 2 — Scene Type** (single_select): |
| 29 | - 纯白底主图(White Background Hero Shot) |
| 30 | - 生活场景图(Lifestyle Shot) |
| 31 | - 创意氛围图(Creative Atmosphere) |
| 32 | - 自定义场景(Let me describe) |
| 33 | |
| 34 | **Question 3 — Aspect Ratio** (single_select): |
| 35 | - 1:1(默认,适合淘宝/Amazon) |
| 36 | - 4:3(横版展示) |
| 37 | - 3:4(竖版/小红书) |
| 38 | - 16:9(Banner/横幅) |
| 39 | |
| 40 | ### Step 3: Generate the Prompt |
| 41 | |
| 42 | Read the reference file at `references/prompt-templates.md` for scene-specific templates and photography parameters, then compose the final prompt. |
| 43 | |
| 44 | #### Prompt Composition Principles |
| 45 | |
| 46 | Nano Banana Pro is a "Thinking" model built on Gemini 3 Pro. It understands intent, physics, and composition. The key principles: |
| 47 | |
| 48 | 1. **Think like a Creative Director, not tag soup.** Write in natural, descriptive English sentences — not comma-separated keyword lists. Nano Banana Pro's text encoder is an LLM that reasons about the prompt before generating. |
| 49 | |
| 50 | 2. **6-element structure** — Every prompt should include: |
| 51 | - **Subject**: Precise description of the product with material, color, and distinguishing features |
| 52 | - **Composition**: Camera angle, framing, how the product fills the frame (~85-90%) |
| 53 | - **Camera & Lens**: Focal length (e.g., 85mm), aperture (e.g., f/8), ISO |
| 54 | - **Lighting**: Specific setup (softbox, key light angle, fill ratio, rim light) |
| 55 | - **Style**: The overall aesthetic (commercial product photography, editorial, etc.) |
| 56 | - **Technical specs**: Resolution and aspect ratio |
| 57 | |
| 58 | 3. **Reference image directive** — Always start with a clear instruction to use the uploaded image as reference: "Using the provided reference image as the product source, ..." |
| 59 | |
| 60 | 4. **Negative instructions** — Include what to exclude: no text, no watermarks, no hands, no distracting elements. |
| 61 | |
| 62 | 5. **Resolution & Aspect Ratio** — Specify the exact output: "Generate at 2K resolution (2048×2048 for 1:1)" or the appropriate dimensions for the chosen ratio. |
| 63 | |
| 64 | #### Output Format |
| 65 | |
| 66 | Present the prompt in a clean code block that the user can copy directly: |
| 67 | |
| 68 | ``` |
| 69 | 📸 Ecom Shot — {Product Name} |
| 70 | ━━━━━━━━━━━━━━━━━━━━━━━━━━━━ |
| 71 | |
| 72 | Scene: {scene type} |
| 73 | Aspect Ratio: {ratio} |
| 74 | Resolution: 2K |
| 75 | |
| 76 | --- Prompt (copy below) --- |
| 77 | |
| 78 | {the generated prompt text} |
| 79 | |
| 80 | --- End Prompt --- |
| 81 | ``` |
| 82 | |
| 83 | After the prompt, add a brief "💡 Tips" section with 1-2 actionable suggestions: |
| 84 | - How to iterate if the result isn't perfect (e.g., "If the lighting feels flat, try adding: 'with dramatic side lighting creating deep shadows'") |
| 85 | - Whether multi-turn editing could help (e.g., "After generating, you can ask Gemini to 'make the background slightly warmer'") |
| 86 | |
| 87 | ### Step 4: Iterate if Needed |
| 88 | |
| 89 | If the user wants to adjust the prompt: |