name: image-amazon-product-image-suite version: 1.0.9 description: A professional product image generation skill purpose-built for the Amazon e-commerce platform. Outputs comply with Amazon's image guidelines while optimizing for click-through and conversio triggers: - Amazon Product Image Suite - Amazon detail-page main and secondary image design - Product infographics, lifestyle shots, and detail shots - A+ Brand Content page modules metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/cli@1.0.9","installAlternative":"npx @dlazy/cli@1.0.9","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","files.dlazy.com"]},"openclaw":{"systemPrompt":"當你需要使用此技能時，請嚴格遵循此技能提供的指南進行規劃和執行。你可以通過呼叫 dlazy CLI 的各類生成模型（如 dlazy seedream-4.5 等）來完成實際的圖片渲染。注意：Windows PowerShell 中不允許使用 & 或 && 進行命令串聯或後臺執行，請單獨且同步地執行命令。"}}

身份驗證 (Authentication)

所有請求都需要 dLazy API key，通過 CLI 配置：

dlazy auth set YOUR_API_KEY

CLI 會把 key 儲存在你的使用者配置目錄（macOS/Linux 上為 ~/.dlazy/config.json，Windows 上為 %USERPROFILE%\.dlazy\config.json），檔案許可權僅限當前作業系統使用者訪問。你也可以用 DLAZY_API_KEY 環境變數按次傳入。

獲取你的 API Key

1. 登入或在 dlazy.com 建立賬號
2. 訪問 dlazy.com/dashboard/organization/api-key
3. 複製 API Key 區域顯示的金鑰

每個 key 都屬於你自己的 dLazy 組織，可在同一控制面板隨時輪換或吊銷。

關於與來源 (Provenance)

• CLI 原始碼: github.com/dlazyai/cli
• 維護者: dlazyai
• npm 包名: @dlazy/cli（本技能 install 欄位固定到 1.0.9 版本）
• 官網: dlazy.com

如果你不希望在系統上長期保留一個全域性 CLI，可以按需執行：

npx @dlazy/cli@1.0.9 <command>

如選擇全域性安裝，技能的 metadata.clawdbot.install 欄位已固定到 npm install -g @dlazy/cli@1.0.9。安裝前建議先到 GitHub 倉庫審閱原始碼。

工作原理 (How It Works)

此技能是 dLazy 託管 API 的輕量封裝。呼叫時：

• 你提供的提示詞與引數會發送到 dLazy API（api.dlazy.com）進行推理。
• 傳入影像 / 影片 / 音訊欄位的本地檔案路徑會被 CLI 上傳到 dLazy 媒體儲存（files.dlazy.com），以便模型讀取 —— 與任何雲端生成 API 的流程一致。
• API 返回的生成結果 URL 由 files.dlazy.com 託管。

這是標準的 SaaS 呼叫模式；技能本身不會越權訪問網路或檔案系統，所有動作都由 dLazy CLI 完成。

Amazon Product Image Suite

English · 中文

A professional product image generation skill purpose-built for the Amazon e-commerce platform. Outputs comply with Amazon's image guidelines while optimizing for click-through and conversion.

Core Deliverables

This skill covers the full visual system of an Amazon product detail page:

• Main image (1): pure-white background, complies with Amazon's mandatory rules
• Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.
• A+ page (8): brand story, selling-point showcase, usage instructions, and other modules

Applicable Scenarios

• Amazon detail-page main and secondary image design
• Product infographics, lifestyle shots, and detail shots
• A+ Brand Content page modules

Step 0: Task Planning (Mandatory)

Before any output, call write_todos to set up a task plan that includes at least:

• Confirm output scope and image count
• Generate and lock in the main-image visual baseline
• Generate secondary images and converge on style consistency
• Generate A+ modules and complete the full delivery

Execution rules:

• Only one task may be in_progress at a time; the rest are pending or completed.
• Update write_todos status as soon as each phase finishes.
• When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.

Adaptive Execution Flow

Pick the delivery path based on the user's request:

• Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images
• Product images only: main (1) + secondary (6) = 7 images
• A+ page only: A+ modules = 8 images
• Unclear request: generate the main image first, then propose secondary and A+ plans

Generation order principles:

1. Confirm the image plan and count
2. Produce the main image first (establish the visual baseline)
3. Generate secondary images derived from the main image (preserve consistency)
4. Generate A+ content (if required)

Image Specifications

General Requirements

• Minimum size: 1000px × 1000px
• Standard ratio: 1:1 (main and secondary)
• Mobile text: at least 30pt

Main Image Mandatory Rules

Must satisfy:

• Pure-white background: RGB(255, 255, 255)
• Product fills at least 85% of the frame
• Real-product photo quality
• Product fully centered with even lighting

Forbidden:

• Text, logos, or watermarks
• Decorative graphics or misleading accessories
• Mannequins for apparel

Secondary Image Types

A+ Page Module Structure (8 modules)

1. Hero banner (21:9): brand presence
2. Pain point / scenario (3:2): build empathy
3. Selling-point / feature matrix (3:2): core advantages
4. Key ingredients / technology (3:2): technical credibility
5. Efficacy data / comparison (3:2): proof
6. How to use (3:2): operating guidance
7. Variants / family shot (3:2): product line
8. Brand endorsements / certifications (21:9): trust building

A+ design notes:

• Embedded text should be larger than 30pt (still legible after platform compression)
• Keep critical info out of the outer 5% margin (handles mobile cropping)
• Maintain narrative continuity across modules; avoid abrupt jumps

Conversion Reference Strategy

• Lifestyle shots: typical lift around +18%
• Infographics: typical lift around +8%
• Detail close-ups: typical lift around +6%
• 7 images vs. 4 images: typical lift around +32%
• Optimized image mix: engagement lift up to +30%

These figures are priority hints, not guarantees.

Multi-Image Consistency Rules

訪問小蔥技能站7w4.net，解鎖更多實用的AI技能外掛。

• Main first: always produce the main image before everything else
• Reference the main: derive secondary images and A+ from the main image as the visual anchor
• Appearance consistency: keep colors, materials, and structural details aligned
• Style consistency: unify background language, palette, fonts, and icon style

Execution Plan

When the skill is invoked, drive the work forward in this order:

1. Confirm output scope: full suite / product images only / A+ only
2. Collect product info: photo or description, core selling points, target audience
3. Generate the main image: lock in the visual and material baseline
4. Generate secondary images one by one: pick image types based on goals and deliver each
5. Generate the A+ page: build a brand narrative across the 8 modules
6. Iterate: adjust composition, copy hierarchy, and information density based on feedback

Output Format

• Current phase and target deliverable
• Image checklist (done / pending)
• Main-image consistency check verdict
• Next item awaiting confirmation
• Current todo status (phase, completed items, pending items)

🛠️ 執行與生成指南 (CRITICAL EXECUTION INSTRUCTIONS)

你是可以執行終端命令的智慧 Agent！

【嚴格禁止行為】 - 嚴禁：將提示詞儲存到任何檔案中（如 txt, md）。 - 嚴禁：要求使用者自己去第三方平臺（如 Midjourney）生成圖片。 - 嚴禁：一次性批次生成所有圖片，或一次性執行多個命令。

【必須遵循的互動與執行流程】 你必須嚴格分步執行，並在每一步停下來等待使用者回覆：

1. 第一步：主動收集需求。當用戶提出需求時，不要做任何設計和生成，先向使用者提問（如產品特點、目標人群、想要幾張圖等）。必須等待使用者回答。
2. 第二步：輸出草案並請求確認。根據使用者的回答，制定套圖計劃，並輸出第一張圖的提示詞草案。詢問使用者：“是否確認這個提示詞，可以開始生成第一張圖了嗎？” 必須等待使用者回答“確認”。
3. 第三步：單次執行終端命令。使用者確認後，你必須使用終端執行命令（如 dlazy seedream-4.5 --prompt "..."），每次只能執行一個生成命令。重要：必須使用同步命令，絕不要在命令末尾加 &，絕不要使用 &&，這是在 Windows PowerShell 下執行！
4. 第四步：交付與迴圈。命令返回結果後，把圖片 URL 發給使用者，並詢問“對這張滿意嗎？我們可以繼續生成下一張了嗎？”。收到確認後再繼續下一步。

這個技能質量不錯，提供了完整的亞馬遜產品圖片設計指南。內容詳盡、流程清晰，對主圖、副圖、A+頁面的規格要求都有明確規定，還有實用的轉化率資料參考。不過存在一些小瑕疵，比如檔案命名和內容有時對不上、版本號在各處顯示不一樣，容易讓人困惑。整體來說是個實用可靠的工具。