{"id":"1b928349-a0b2-4f1f-9411-5fd7b8fd4dc0","entityType":"agent","slug":"clawhub-dlazyai-dlazy-image-amazon-product-image-suite","name":"亚马逊商品图套件 Amazon Product Image Suite","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dlazyai-dlazy-image-amazon-product-image-suite","canonicalPath":"/agent/clawhub-dlazyai-dlazy-image-amazon-product-image-suite","generatedAt":"2026-10-10T08:10:18.801Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":null},"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","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.8K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-amazon-product-image-suite","sourceUrl":"https://clawhub.ai/dlazyai/dlazy-image-amazon-product-image-suite","homepage":"https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dlazyai/dlazy-image-amazon-product-image-suite","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":74,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"亚马逊商品图套件 Amazon Product Image Suite technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":null},"stars":null,"forks":null,"downloads":4767,"packageName":null,"latestVersion":"1.3.27","tractionLabel":"4.8K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T04:53:18.304Z","lastCrawledAt":"2026-10-09T04:53:18.304Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T04:53:18.304Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.27","createdAt":"2026-10-08T01:13:40.356Z","changelog":"例行版本更新 2026-10-08","fileCount":4,"zipByteSize":12295},{"version":"1.3.26","createdAt":"2026-10-04T01:12:23.222Z","changelog":"例行版本更新 2026-10-04","fileCount":4,"zipByteSize":12297},{"version":"1.3.25","createdAt":"2026-10-02T04:55:10.698Z","changelog":"例行版本更新 2026-10-02","fileCount":4,"zipByteSize":12214},{"version":"1.3.24","createdAt":"2026-09-30T01:11:40.719Z","changelog":"例行版本更新 2026-09-30","fileCount":4,"zipByteSize":12203},{"version":"1.3.23","createdAt":"2026-09-28T02:10:06.241Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":12167},{"version":"1.3.22","createdAt":"2026-09-28T01:12:26.803Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":12226},{"version":"1.3.21","createdAt":"2026-09-24T01:48:57.544Z","changelog":"例行版本更新 2026-09-24","fileCount":4,"zipByteSize":12349},{"version":"1.3.20","createdAt":"2026-09-22T01:10:16.357Z","changelog":"例行版本更新 2026-09-22","fileCount":4,"zipByteSize":12352}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-amazon-product-image-suite","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-image-amazon-product-image-suite` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/dlazyai/dlazy-image-amazon-product-image-suite before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T08:10:18.797Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-image-amazon-product-image-suite/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":null},"readme":"Skill: 亚马逊商品图套件 Amazon Product Image Suite\n\nOwner: dlazyai\n\nSummary: 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\n\nTags: latest:1.3.27\n\nVersion history:\n\nv1.3.27 | 2026-10-08T01:13:40.356Z | user\n\n例行版本更新 2026-10-08\n\nv1.3.26 | 2026-10-04T01:12:23.222Z | user\n\n例行版本更新 2026-10-04\n\nv1.3.25 | 2026-10-02T04:55:10.698Z | user\n\n例行版本更新 2026-10-02\n\nv1.3.24 | 2026-09-30T01:11:40.719Z | user\n\n例行版本更新 2026-09-30\n\nv1.3.23 | 2026-09-28T02:10:06.241Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.22 | 2026-09-28T01:12:26.803Z | user\n\n例行版本更新 2026-09-28\n\nv1.3.21 | 2026-09-24T01:48:57.544Z | user\n\n例行版本更新 2026-09-24\n\nv1.3.20 | 2026-09-22T01:10:16.357Z | user\n\n例行版本更新 2026-09-22\n\nv1.3.19 | 2026-09-20T01:14:45.189Z | user\n\n例行版本更新 2026-09-20\n\nv1.3.18 | 2026-09-18T01:36:37.998Z | user\n\n例行版本更新 2026-09-18\n\nv1.3.17 | 2026-09-14T01:11:26.699Z | user\n\n例行版本更新 2026-09-14\n\nv1.3.16 | 2026-09-10T01:09:43.841Z | user\n\n例行版本更新 2026-09-10\n\nv1.3.15 | 2026-09-08T01:10:21.220Z | user\n\n例行版本更新 2026-09-08\n\nv1.3.14 | 2026-09-07T01:13:17.729Z | user\n\n例行版本更新 2026-09-07\n\nv1.3.13 | 2026-09-04T01:15:35.661Z | user\n\n例行版本更新 2026-09-04\n\nv1.3.12 | 2026-09-02T01:10:17.645Z | user\n\n例行版本更新 2026-09-02\n\nv1.3.11 | 2026-08-31T02:51:03.599Z | user\n\n源码仓库迁移至 github.com/dlazy-ai/cli\n\nv1.3.10 | 2026-08-24T09:21:59.322Z | user\n\nRestore Chinese display name\n\nv1.3.9 | 2026-08-17T09:04:00.144Z | user\n\nRestore Chinese display name\n\nv1.3.8 | 2026-08-10T05:45:35.742Z | user\n\nRestore Chinese display name\n\nv1.3.7 | 2026-08-10T04:00:11.888Z | user\n\nRestore Chinese display name\n\nv1.3.6 | 2026-07-21T02:16:28.237Z | auto\n\n- Bumped required CLI version from @dlazy/cli@1.2.2 to @dlazy/cli@1.2.3 in install instructions and metadata.\n- Updated documentation in both SKILL.md and SKILL-cn.md to reflect the new CLI version for global and NPX usage.\n- Removed the file skill-card.md from the skill package.\n\nv1.3.5 | 2026-07-20T05:54:38.326Z | user\n\n规范 dlazy- 前缀命名，补充中文显示名\n\nv1.3.4 | 2026-07-17T10:36:51.952Z | auto\n\n- Updated version to 1.3.4.\n- Documentation changes: revised SKILL.md and SKILL-cn.md files.\n- Removed the file skill-card.md.\n- No functional or code changes; updates are limited to docs and supporting materials.\n\nv1.2.2 | 2026-07-17T08:42:37.640Z | auto\n\n- Version bumped down from 1.2.2 to 1.2.1.\n- Documentation updated in both English and Chinese (`SKILL.md`, `SKILL-cn.md`).\n- The `skill-card.md` file was removed for this release.\n- No functional or API changes; this revision focuses on maintenance and documentation housekeeping.\n\nv1.3.3 | 2026-07-09T01:46:54.983Z | user\n\nset Chinese display name for CN search\n\nv1.3.2 | 2026-07-09T01:46:40.862Z | user\n\nset Chinese display name for CN search\n\nv1.3.1 | 2026-07-09T01:28:23.868Z | user\n\nset Chinese display name for CN search\n\nv1.3.0 | 2026-07-07T19:43:27.575Z | auto\n\n- Updated version from 1.2.1 to 1.3.0.\n- Documentation improvements in English (SKILL.md) and Chinese (SKILL-cn.md).\n- No functional or code changes; improvements are limited to file documentation.\n\nv1.2.1 | 2026-07-07T18:30:41.302Z | auto\n\n- Added Chinese summary to the description field for bilingual clarity.\n- Removed redundant file: skill-card.md.\n- Minor formatting and wording updates in skill documentation.\n- No functional or API-level changes.\n\nv1.2.0 | 2026-06-02T10:03:51.157Z | auto\n\nVersion 1.2.0\n\n- Updated the CLI dependency to use @dlazy/cli@1.2.0 (was 1.0.9).\n- Adjusted install commands and metadata to reference the new CLI version.\n- Removed the redundant skill-card.md file.\n- Minor formatting and structure improvements in documentation files.\n\nv1.1.2 | 2026-06-02T01:40:34.850Z | user\n\nUpdate model skills (names/params refreshed); add search-audio/image/video\n\nv1.1.1 | 2026-05-06T14:13:18.200Z | auto\n\n- Version bump from 1.1.0 to 1.1.1.\n- Documentation updated in SKILL.md and SKILL-cn.md; no functional or logic changes.\n- No impact on usage or output—content and execution remain unchanged.\n\nv1.1.0 | 2026-05-01T07:56:24.367Z | auto\n\nVersion 1.1.0\n\n- Added and documented support for `dlazy login` (device-code authentication), providing an easier and more secure recommended login method.\n- Updated authentication instructions: now feature both the new login flow and legacy manual API key methods.\n- Clarified and reorganized the authentication section, separating \"login\" and \"manual key\" processes.\n- No changes to triggers, deliverables, or execution flow.\n\nv1.0.9 | 2026-04-30T10:22:36.051Z | user\n\nSync to CLI 1.0.9 with cliWarning support\n\nv1.0.6 | 2026-04-29T02:46:09.221Z | user\n\nrepublish from project source; bump @dlazy/cli to 1.0.8\n\nv1.0.5 | 2026-04-29T02:35:47.953Z | user\n\nbump @dlazy/cli to 1.0.8\n\nv1.0.4 | 2026-04-27T08:03:51.594Z | user\n\nReduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.\n\nv1.0.3 | 2026-04-27T07:42:34.915Z | user\n\nAdd provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/cli@1.0.6' install alternative, normalise Chinese auth-error instruction wording.\n\nv1.0.2 | 2026-04-24T04:09:09.354Z | auto\n\nimage-amazon-product-image-suite v1.0.2\n\n- Documentation updated in all supported languages for greater clarity and accuracy.\n- Minor corrections and formatting improvements across SKILL.md, SKILL-en.md, and SKILL-cn.md.\n- No changes to core functionality or usage instructions.\n\nv1.0.1 | 2026-04-24T03:35:33.309Z | auto\n\n- Added authentication instructions: now requires configuration of dLazy API key before use.\n- Updated recommended CLI version to @dlazy/cli@1.0.6.\n- Made no changes to product image workflow or execution process.\n\nv1.0.0 | 2026-04-23T05:44:14.443Z | auto\n\nInitial release of image-amazon-product-image-suite.\n\n- 专为亚马逊平台设计，实现一站式产品图、详情图、A+页面内容智能生成\n- 覆盖主图、副图、A+页面等电商视觉全流程，自动规划及分步执行\n- 严格遵循亚马逊图片规范、分辨率和内容合规要求\n- 自适应交互：主动收集需求，逐张生成与用户实时确认，支持任务追踪及返工\n- 融合转化率优化与多图风格一致性策略\n\nArchive index:\n\nArchive v1.3.27: 4 files, 12295 bytes\n\nFiles: skill-card.md (2035b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.27:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.27:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422020356\n}\n\nFile v1.3.27:skill-card.md\n\n## Description:\n\nGuides agents through planning and generating Amazon product main images, secondary images, and A+ content using dLazy image tools.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSellers and creative teams use this skill to plan and produce coordinated Amazon listing images and A+ page visuals, reviewing each image before continuing.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Product prompts and supplied media may be sent to dLazy's cloud service.\n\nMitigation: Use only content you are comfortable sharing with dLazy; review media before submission.\n\nRisk: The CLI may store an API key in the local user profile.\n\nMitigation: Use a per-run environment key when persistent storage is undesirable, and rotate or revoke keys if exposed.\n\nRisk: Installing the third-party CLI introduces a package supply-chain dependency.\n\nMitigation: Review the package and source before installation if supply-chain assurance is required.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI source (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown guidance, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with image checklists, prompts, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Stepwise generation with user approval between images; main-image consistency checks.]\n\n## Skill Version(s):\n\n1.3.27 (source: server-resolved release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.27:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.26: 4 files, 12297 bytes\n\nFiles: skill-card.md (2154b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.26:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.26:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.26\",\n  \"publishedAt\": 1791076343222\n}\n\nFile v1.3.26:skill-card.md\n\n## Description:\n\nGuides the creation of Amazon product listing images and A+ content modules with dLazy image generation.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSellers and creative teams use this skill to plan and generate Amazon listing main images, secondary product visuals, and A+ page modules.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Using the skill requires a dLazy API key and sends prompts and referenced product media to dLazy's cloud service.\n\nMitigation: Review the service's terms and data handling before sharing sensitive product material; protect the API key.\n\nRisk: The artifact contains inconsistent CLI version references.\n\nMitigation: Confirm the intended CLI version before installing or running it.\n\nRisk: Generated product imagery or text may misrepresent the product or fail marketplace requirements.\n\nMitigation: Review images and claims against the actual product and applicable listing requirements before publishing.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI source (skill metadata link; not verified release provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Shell commands, Images]\n\n**Output Format:** [Markdown plan and progress updates with generated image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Main image, secondary images, and optional A+ modules are generated individually through the dLazy service.]\n\n## Skill Version(s):\n\n1.3.26 (source: ClawHub release metadata; artifact frontmatter says 1.3.6)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.26:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.25: 4 files, 12214 bytes\n\nFiles: skill-card.md (1895b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.25:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.25:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.25\",\n  \"publishedAt\": 1790916910698\n}\n\nFile v1.3.25:skill-card.md\n\n## Description:\n\nPlans and generates Amazon product listing images and A+ content with a consistent visual style.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSellers and designers use this skill to plan and generate Amazon main images, secondary product images, and A+ page visuals using the dLazy service.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Product prompts and selected media are sent to the dLazy cloud service.\n\nMitigation: Upload only content approved for the service and review its data handling before use.\n\nRisk: Signing in can save an API key on the local device.\n\nMitigation: Use DLAZY_API_KEY when persistent local credential storage is not desired.\n\nRisk: The skill text contains conflicting dLazy CLI version references.\n\nMitigation: Verify the intended @dlazy/cli version and review the package before installation.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI repository](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with image plans, prompts, progress checklists, and generated image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Images are generated one at a time after user confirmation.]\n\n## Skill Version(s):\n\n1.3.25 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.25:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.24: 4 files, 12203 bytes\n\nFiles: skill-card.md (1943b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.24:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.24:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.24\",\n  \"publishedAt\": 1790730700719\n}\n\nFile v1.3.24:skill-card.md\n\n## Description:\n\nGuides agents in planning and generating Amazon product listing images and A+ content with the dLazy image-generation CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nE-commerce sellers and designers use this skill to plan and generate main images, secondary images, and A+ content for Amazon product pages.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected product media are sent to dLazy's cloud services.\n\nMitigation: Review prompts and media for sensitive content before using the CLI.\n\nRisk: The CLI can store the API key in local configuration.\n\nMitigation: Protect the local configuration or use the DLAZY_API_KEY environment-variable option.\n\nRisk: The artifact frontmatter version differs from the ClawHub release version.\n\nMitigation: Ask the publisher to reconcile the version metadata before relying on the artifact version.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI repository (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with image links and command snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Stepwise main, secondary, and A+ image planning and delivery.]\n\n## Skill Version(s):\n\n1.3.24 (source: ClawHub release evidence; artifact frontmatter lists 1.3.6)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.24:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.23: 4 files, 12167 bytes\n\nFiles: skill-card.md (1818b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.23:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.23:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.23\",\n  \"publishedAt\": 1790561406241\n}\n\nFile v1.3.23:skill-card.md\n\n## Description:\n\nGuides agents through planning and generating Amazon product listing images and A+ content using dLazy's CLI and hosted image service.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSellers and creative teams use this skill to plan and generate Amazon listing main images, secondary images, and A+ brand content, reviewing each image before continuing.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Using the third-party CLI and hosted service requires an API key.\n\nMitigation: Review the CLI package before installation; protect the key and rotate or revoke it if needed.\n\nRisk: Generation prompts and selected local media may be sent to dLazy's cloud service.\n\nMitigation: Confirm each generation command and share only prompts and files appropriate for upload.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI source (skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with image URLs and inline shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Images are generated individually after user confirmation and hosted by dLazy.]\n\n## Skill Version(s):\n\n1.3.23 (source: ClawHub release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.23:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.22: 4 files, 12226 bytes\n\nFiles: skill-card.md (1910b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.22:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.22:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.22\",\n  \"publishedAt\": 1790557946803\n}\n\nFile v1.3.22:skill-card.md\n\n## Description:\n\nHelps sellers plan and generate Amazon product listing images and A+ content using dLazy's image-generation service.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nAmazon sellers and designers use this skill to plan and generate a main product image, supporting images, and A+ page modules with a consistent visual style.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Product prompts and referenced media are sent to dLazy-hosted services.\n\nMitigation: Use only product content approved for third-party processing.\n\nRisk: The dLazy CLI may persist an API key in local configuration.\n\nMitigation: Use the documented DLAZY_API_KEY environment variable when persistent storage is undesirable.\n\nRisk: Installing and running a third-party CLI introduces software-supply-chain exposure.\n\nMitigation: Review the @dlazy/cli package and source before global installation.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI documentation and source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Images, Text, Guidance]\n\n**Output Format:** [Hosted image URLs and Markdown status updates]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Delivers images individually for review before continuing.]\n\n## Skill Version(s):\n\n1.3.22 (source: ClawHub release; skill frontmatter lists 1.3.6)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.22:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.21: 4 files, 12349 bytes\n\nFiles: skill-card.md (2288b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.21:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.3.21:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.21\",\n  \"publishedAt\": 1790214537544\n}\n\nFile v1.3.21:skill-card.md\n\n## Description:\n\nA professional product image generation skill for Amazon product listings that helps agents plan and generate compliant main images, secondary images, and A+ Brand Content modules.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nE-commerce sellers, designers, and developers use this skill to plan and generate Amazon-ready product listing imagery, including main images, secondary infographics, lifestyle and detail images, and A+ Brand Content modules.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill installs and invokes a third-party npm package and stores a dLazy API key locally.\n\nMitigation: Review the dLazy CLI package and intended version before installation, protect the local API key file, and rotate or revoke the key when access changes.\n\nRisk: Product prompts and local media can be sent to dLazy cloud services for generation.\n\nMitigation: Only provide product images, media, and copy that are approved for upload to dLazy's cloud service.\n\nRisk: Generated marketplace imagery or claims may still be inaccurate or noncompliant for a specific listing.\n\nMitigation: Review generated images, text, visual claims, and Amazon guideline compliance before publication.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown status updates with inline shell commands and generated image URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Guides iterative image generation through dLazy CLI commands, with user confirmation between generated assets.]\n\n## Skill Version(s):\n\n1.3.21 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.3.21:SKILL-cn.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories complete and clearly identifiable |\n| Size reference | Show real-world size | Use a familiar object as a scale reference |\n\n## A+ Page Module Structure (8 modules)\n\n1. Hero banner (21:9): brand presence\n2. Pain point / scenario (3:2): build empathy\n3. Selling-point / feature matrix (3:2): core advantages\n4. Key ingredients / technology (3:2): technical credibility\n5. Efficacy data / comparison (3:2): proof\n6. How to use (3:2): operating guidance\n7. Variants / family shot (3:2): product line\n8. Brand endorsements / certifications (21:9): trust building\n\nA+ design notes:\n\n- Embedded text should be larger than 30pt (still legible after platform compression)\n- Keep critical info out of the outer 5% margin (handles mobile cropping)\n- Maintain narrative continuity across modules; avoid abrupt jumps\n\n## Conversion Reference Strategy\n\n- Lifestyle shots: typical lift around +18%\n- Infographics: typical lift around +8%\n- Detail close-ups: typical lift around +6%\n- 7 images vs. 4 images: typical lift around +32%\n- Optimized image mix: engagement lift up to +30%\n\nThese figures are priority hints, not guarantees.\n\n## Multi-Image Consistency Rules\n\n- Main first: always produce the main image before everything else\n- Reference the main: derive secondary images and A+ from the main image as the visual anchor\n- Appearance consistency: keep colors, materials, and structural details aligned\n- Style consistency: unify background language, palette, fonts, and icon style\n\n## Execution Plan\n\nWhen the skill is invoked, drive the work forward in this order:\n\n1. Confirm output scope: full suite / product images only / A+ only\n2. Collect product info: photo or description, core selling points, target audience\n3. Generate the main image: lock in the visual and material baseline\n4. Generate secondary images one by one: pick image types based on goals and deliver each\n5. Generate the A+ page: build a brand narrative across the 8 modules\n6. Iterate: adjust composition, copy hierarchy, and information density based on feedback\n\n## Output Format\n\n- Current phase and target deliverable\n- Image checklist (done / pending)\n- Main-image consistency check verdict\n- Next item awaiting confirmation\n- Current todo status (phase, completed items, pending items)\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.3.20: 4 files, 12352 bytes\n\nFiles: skill-card.md (2129b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nFile v1.3.20:SKILL.md\n\n---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selling-point showcase, usage instructions, and other modules\n\n## Applicable Scenarios\n\n- Amazon detail-page main and secondary image design\n- Product infographics, lifestyle shots, and detail shots\n- A+ Brand Content page modules\n\n## Step 0: Task Planning (Mandatory)\n\nBefore any output, call `write_todos` to set up a task plan that includes at least:\n\n- Confirm output scope and image count\n- Generate and lock in the main-image visual baseline\n- Generate secondary images and converge on style consistency\n- Generate A+ modules and complete the full delivery\n\nExecution rules:\n\n- Only one task may be `in_progress` at a time; the rest are `pending` or `completed`.\n- Update `write_todos` status as soon as each phase finishes.\n- When the user requests rework, redesign, or new assets, add or re-order tasks and return to the corresponding phase.\n\n## Adaptive Execution Flow\n\nPick the delivery path based on the user's request:\n\n- Full suite: main (1) + secondary (6) + A+ (8) = 12–17 images\n- Product images only: main (1) + secondary (6) = 7 images\n- A+ page only: A+ modules = 8 images\n- Unclear request: generate the main image first, then propose secondary and A+ plans\n\nGeneration order principles:\n\n1. Confirm the image plan and count\n2. Produce the main image first (establish the visual baseline)\n3. Generate secondary images derived from the main image (preserve consistency)\n4. Generate A+ content (if required)\n\n## Image Specifications\n\n### General Requirements\n\n- Minimum size: 1000px × 1000px\n- Standard ratio: 1:1 (main and secondary)\n- Mobile text: at least 30pt\n\n### Main Image Mandatory Rules\n\nMust satisfy:\n\n- Pure-white background: RGB(255, 255, 255)\n- Product fills at least 85% of the frame\n- Real-product photo quality\n- Product fully centered with even lighting\n\nForbidden:\n\n- Text, logos, or watermarks\n- Decorative graphics or misleading accessories\n- Mannequins for apparel\n\n## Secondary Image Types\n\n| Type | Purpose | Design Notes |\n| --- | --- | --- |\n| Infographic | Highlight selling points / feature comparison | 4–6 selling points, callout lines pointing to features, icons reinforce visuals |\n| Multi-angle | Show the product from different angles | Consistent lighting, clean backgrounds, usually 2 shots |\n| Detail close-up | Show materials and craftsmanship | Macro composition, emphasize texture |\n| Lifestyle | Show real usage scenarios | Target user in a real environment, usually 2 shots |\n| Variant showcase | Show color or style options | All variants arranged with consistent layout and scale |\n| Package contents | Show what's in the box | All accessories comple\n\nArchive v1.3.19: 4 files, 12429 bytes\n\nFiles: skill-card.md (2471b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)\n\nArchive v1.3.18: 4 files, 12619 bytes\n\nFiles: skill-card.md (2842b), SKILL-cn.md (10437b), SKILL.md (10437b), _meta.json (158b)","readmeExcerpt":"Skill: 亚马逊商品图套件 Amazon Product Image Suite Owner: dlazyai Summary: 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 Tags: latest:1.3.27 Version history: v1.3.27 | 2026-10-08T01:13:40.356Z | user 例行版本更新 2026-10-08 v1.3.26 | 2026-10-04T01:12:23.222Z | user 例行版本更新 2026-10-04 v1.3.","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"},{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selli"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-image-amazon-product-image-suite\",\n  \"version\": \"1.3.27\",\n  \"publishedAt\": 1791422020356\n}"},{"path":"skill-card.md","content":"## Description:\n\nGuides agents through planning and generating Amazon product main images, secondary images, and A+ content using dLazy image tools.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nSellers and creative teams use this skill to plan and produce coordinated Amazon listing images and A+ page visuals, reviewing each image before continuing.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Product prompts and supplied media may be sent to dLazy's cloud service.\n\nMitigation: Use only content you are comfortable sharing with dLazy; review media before submission.\n\nRisk: The CLI may store an API key in the local user profile.\n\nMitigation: Use a per-run environment key when persistent storage is undesirable, and rotate or revoke keys if exposed.\n\nRisk: Installing the third-party CLI introduces a package supply-chain dependency.\n\nMitigation: Review the package and source before installation if supply-chain assurance is required.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-image-amazon-product-image-suite)\n- [dLazy CLI source (listed in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown guidance, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with image checklists, prompts, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Stepwise generation with user approval between images; main-image consistency checks.]\n\n## Skill Version(s):\n\n1.3.27 (source: server-resolved release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"SKILL-cn.md","content":"---\nname: dlazy-image-amazon-product-image-suite\nversion: 1.3.6\ndescription: 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\ntriggers:\n  - Amazon Product Image Suite\n  - Amazon detail-page main and secondary image design\n  - Product infographics, lifestyle shots, and detail shots\n  - A+ Brand Content page modules\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/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\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# 亚马逊商品图套件 Amazon Product Image Suite\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA 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.\n\n## Core Deliverables\n\nThis skill covers the full visual system of an Amazon product detail page:\n\n- Main image (1): pure-white background, complies with Amazon's mandatory rules\n- Secondary images (6): infographics, multi-angle shots, lifestyle scenes, detail close-ups, etc.\n- A+ page (8): brand story, selli"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1276,"uniquenessScore":39,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T04:53:18.304Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T08:10:18.801Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}